sxlxc/overleaf-server-arm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

first commit

Browse Source
This commit is contained in:
Yu Cong
2025-04-24 13:11:28 +08:00
commit ff9c54d5e4
5960 changed files with 834111 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
libraries/object-persistor/.gitignore vendored Normal file
View File

@@ -0,0 +1,4 @@
/node_modules
*.swp
.npmrc

6
libraries/object-persistor/.mocharc.json Normal file
View File

@@ -0,0 +1,6 @@
{
"ui": "bdd",
"recursive": "true",
"reporter": "spec",
"require": "./test/Init"
}

1
libraries/object-persistor/.nvmrc Normal file
View File

@@ -0,0 +1 @@
20.18.2

1
libraries/object-persistor/.prettierignore Normal file
View File

@@ -0,0 +1 @@
node_modules

662
libraries/object-persistor/LICENSE Normal file
View File

@@ -0,0 +1,662 @@
GNU AFFERO GENERAL PUBLIC LICENSE
Version 3, 19 November 2007
Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU Affero General Public License is a free, copyleft license for
software and other kinds of works, specifically designed to ensure
cooperation with the community in the case of network server software.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
our General Public Licenses are intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
Developers that use our General Public Licenses protect your rights
with two steps: (1) assert copyright on the software, and (2) offer
you this License which gives you legal permission to copy, distribute
and/or modify the software.
A secondary benefit of defending all users' freedom is that
improvements made in alternate versions of the program, if they
receive widespread use, become available for other developers to
incorporate. Many developers of free software are heartened and
encouraged by the resulting cooperation. However, in the case of
software used on network servers, this result may fail to come about.
The GNU General Public License permits making a modified version and
letting the public access it on a server without ever releasing its
source code to the public.
The GNU Affero General Public License is designed specifically to
ensure that, in such cases, the modified source code becomes available
to the community. It requires the operator of a network server to
provide the source code of the modified version running there to the
users of that server. Therefore, public use of a modified version, on
a publicly accessible server, gives the public access to the source
code of the modified version.
An older license, called the Affero General Public License and
published by Affero, was designed to accomplish similar goals. This is
a different license, not a version of the Affero GPL, but Affero has
released a new version of the Affero GPL which permits relicensing under
this license.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU Affero General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Remote Network Interaction; Use with the GNU General Public License.
Notwithstanding any other provision of this License, if you modify the
Program, your modified version must prominently offer all users
interacting with it remotely through a computer network (if your version
supports such interaction) an opportunity to receive the Corresponding
Source of your version by providing access to the Corresponding Source
from a network server at no charge, through some standard or customary
means of facilitating copying of software. This Corresponding Source
shall include the Corresponding Source for any work covered by version 3
of the GNU General Public License that is incorporated pursuant to the
following paragraph.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the work with which it is combined will remain governed by version
3 of the GNU General Public License.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU Affero General Public License from time to time. Such new versions
will be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU Affero General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU Affero General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU Affero General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If your software can interact with users remotely through a computer
network, you should also make sure that it provides a way for users to
get its source. For example, if your program is a web application, its
interface could display a "Source" link that leads users to an archive
of the code. There are many ways you could offer source, and different
solutions will be better for different programs; see section 13 for the
specific requirements.
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU AGPL, see
<http://www.gnu.org/licenses/>.

314
libraries/object-persistor/README.md Normal file
View File

@@ -0,0 +1,314 @@
# @overleaf/object-persistor
Stores arbitrary objects in multiple backends, with support for falling back to a secondary backend if the object can't be found in the primary.
Contains a workaround within the GCS backend to allow lifecycle rules to keep objects for a set period of time from deletion, which can't currently be accomplished with GCS's own rules. (See configuration-specific notes later)
## Backends available
- S3
- GCS
- Filesystem (FS)
## Getting started
```JavaScript
// import the module
const ObjectPersistor = require('object-persistor')
const config = {
// see 'Configuration' section below
}
// create a new persistor
const Persistor = ObjectPersistor(config)
```
### Errors
Errors returned by persistor methods are all derived from `OError` (`@overleaf/o-error`.) To perform `instanceof` checks, you can use the `Errors` object from the persistor module:
```JavaScript
const ObjectPersistor = require('object-persistor')
const { Errors } = ObjectPersistor
```
### Methods
#### sendStream
```JavaScript
async function sendStream(bucketName, key, readStream, opts = {})
```
Uploads a stream to the backend.
- `bucketName`: The name of the bucket to upload to
- `key`: The key for the uploaded object
- `readStream`: The data stream to upload
- `opts` (optional):
- `sourceMd5`: The md5 hash of the source data, if known. The uploaded data will be compared against this and the operation will fail if it does not match. If omitted, the md5 is calculated as the data is uploaded instead, and verified against the backend.
- `contentType`: The content type to write in the object metadata
- `contentEncoding`: The content encoding to write in the object metadata
##### Notes
When using a secondary persistor, this method uploads only to the primary.
If an object already exists at the specified key, it will be overwritten.
#### getObjectStream
```JavaScript
async function getObjectStream(bucketName, key, opts = {})
```
Retrieves a stream from the backend, for reading
- `bucketName`: The name of the bucket to download from
- `key`: The key for the object
- `opts` (optional):
- `start`, `end`: Downloads a byte range from the object. Specify both `start` and `end`. `end` is inclusive.
##### Returns
A `stream.Readable` to read the data.
##### Notes
When using a secondary persistor, this method will fall back to retrieving the object from the secondary if it does not exist on the primary.
#### getRedirectUrl
```JavaScript
async function getRedirectUrl(bucketName, key)
```
Gets a signed link directly to the backend, if possible. This can be used to download the data directly, instead of proxying it.
- `bucketName`: The name of the bucket to download from
- `key`: The key for the object
##### Returns
A `string` containing the signed link, or `null` if a link cannot be generated.
##### Notes
In the case of `null`, you should fall back to `getObjectStream` as sometimes signed links cannot be generated.
Do not use this method if you are using a secondary persistor, as this mechanism does not check to see if the object actually exists - so cannot provide a fallback.
#### getObjectSize
```JavaScript
async function getObjectSize(bucketName, key)
```
Returns the size of the stored data
- `bucketName`: The name of the bucket to download from
- `key`: The key for the object
##### Returns
An integer containing the size, in bytes.
##### Notes
When using a secondary persistor this method returns the size from the secondary persistor, if not found on the primary.
#### getObjectMd5Hash
```JavaScript
async function getObjectMd5Hash(bucketName, key)
```
Returns the MD5 hash of the stored data
- `bucketName`: The name of the bucket to download from
- `key`: The key for the object
##### Returns
A string containing the hex representation of the MD5 hash
##### Notes
When using a secondary persistor this method returns the hash from the secondary persistor, if not found on the primary.
#### deleteFile
```JavaScript
async function deleteFile(bucketName, key)
```
Deletes an object
- `bucketName`: The name of the bucket to delete from
- `key`: The key for the object
##### Notes
When using a secondary persistor, this deletes the object from _both_ persistors.
#### deleteDirectory
```JavaScript
async function deleteDirectory(bucketName, key)
```
Deletes a directory (all object whose keys start with the supplied `key`)
- `bucketName`: The name of the bucket to delete from
- `key`: The key prefix for the objects
##### Notes
When using a secondary persistor, this deletes the objects from _both_ persistors.
#### directorySize
```JavaScript
async function directorySize(bucketName, key)
```
Returns the size of a directory (all objects whose keys start with the supplied `key`)
- `bucketName`: The name of the bucket to examine
- `key`: The key prefix for the objects
##### Returns
An integer containing the size, in bytes
##### Notes
When using a secondary persistor, this returns the value from the secondary persistor if no objects are found on the primary.
#### checkIfObjectExists
```JavaScript
async function checkIfObjectExists(bucketName, key)
```
Returns whether an object exists
- `bucketName`: The name of the bucket to examine
- `key`: The key for the object
##### Returns
A boolean representing whether the object exists
##### Notes
When using a secondary persistor, returns true if the object exists on either the primary or secondary.
#### copyObject
```JavaScript
async function copyObject(bucketName, sourceKey, destKey)
```
Copies a object to another key, within a bucket.
- `bucketName`: The name of the bucket in which to copy the object
- `sourceKey`: The key for the object to be copied
- `destKey`: The key to which the object should be copied
##### Notes
Can only copy objects within a single bucket. To copy objects in any other way, pass the stream returned from `getObjectStream` to `sendStream`
If an object already exists at the specified key, it will be overwritten.
#### sendFile
```JavaScript
async function sendFile(bucketName, key, fsPath)
```
Uploads a file from the local disk.
- `bucketName`: The name of the bucket to upload to
- `key`: The key for the uploaded object
- `fsPath`: The path on disk to the file for uploading
##### Notes
When using a secondary persistor, this method uploads only to the primary.
If an object already exists at the specified key, it will be overwritten.
This method is designed for applications which may write temporary data out to the disk before uploading.
## Configuration
An object with the relevant configuration should be passed to the main function returned from the module. The object contains both common and backend-specific parameters.
### Common parameters
- `backend` (required): String specifying the primary persistor to use as the storage backend. Must be one of `s3`, `gcs` or `fs`.
- `signedUrlExpiryInMs`: Time before expiry (in milliseconds) of signed URLs
### FS-specific parameters
- `useSubdirectories`: If true, files will be stored in subdirectories on the filesystem. By default, the directory structure is flattened and slashes in the object keys are replaced with underscores.
#### Notes
For the `FS` persistor, the `bucketName` should be the full path to the folder on disk where the files are stored.
### S3-specific parameters
- `s3.key` (required): The AWS access key ID
- `s3.secret` (required): The AWS secret access key
- `s3.partSize`: The part size for S3 uploads. Defaults to 100 megabytes.
- `s3.httpOptions`: HTTP options passed directly to the [S3 constructor](https://docs.aws.amazon.com/AWSJavaScriptSDK/latest/AWS/S3.html#constructor-property).
- `s3.maxRetries`: The number of times the S3 client will retry in case of an error
- `s3.endpoint`: For testing - overrides the S3 endpoint to use a different service (e.g. a fake S3 server)
- `s3.pathStyle`: For testing - use old path-style URLs, for services that do not support subdomain-based access
- `s3BucketCreds`: A JSON-encoded string specifying different S3 credentials for accessing different buckets, in the following format. These credentials override the default ones configured in the main `s3` settings:
```json
{
"bucketName": {
"auth_key": "your aws access key ID",
"auth_secret": "your aws secret access key"
}
}
```
#### Notes
In order for server-side MD5 generation to work, uploads must be below the `partSize`. Otherwise a multipart upload will be used, and the S3 `eTag` which is used to retrieve the MD5 will not be the MD5 hash of the uploaded object. In these cases, we download the data and calculate the MD5 manually.
For verification during upload, we use S3's checksum mechanism to verify the integrity of the uploaded data, but when explicitly retrieving the md5 hash this will download the entire object if its size is above the part size.
### GCS-specific parameters
GCS authentication is configured automatically via the local service account, or the `GOOGLE_APPLICATION_CREDENTIALS` environment variable.
- `gcs.unlockBeforeDelete`: unlock an event-based hold before deleting. default false (see notes)
- `gcs.deletedBucketSuffix`: if present, copy the object to a bucket with this suffix before deletion (see notes)
- `gcs.deleteConcurrency`: when recursively deleting a directory, the maximum number of delete requests that will be used at once (default 50)
- `gcs.unsignedUrls`: For testing - do not sign GCS download URLs
- `gcs.endpoint.apiEndpoint`: For testing - specify a different GCS endpoint to use
- `gcs.endpoint.projectId`: For testing - the GCS project ID to supply to the overridden backend
#### Notes
In order to support deletion after a period, the GCS persistor allows usage of a two-bucket system. The main bucket contains the live objects, and on delete the objects are first copied to a 'deleted' bucket, and then deleted from the main one. The 'deleted' bucket is then expected to have a lifecycle policy applied to delete objects after a set period.
In order to prevent accidental deletion from outside this mechanism, an event-based-hold can be applied by default on the main bucket. This will be unlocked _after_ the object has been copied to the 'deleted' bucket so that the object can then be deleted from the main bucket.
## Contributing
Contributions should pass lint, formatting and unit test checks. To run these, use
```
npm run test
```
There are no acceptance tests in this module, but https://github.com/overleaf/filestore/ contains a comprehensive set of acceptance tests that use this module. These should also pass, with the changes.

10
libraries/object-persistor/buildscript.txt Normal file
View File

@@ -0,0 +1,10 @@
object-persistor
--dependencies=None
--docker-repos=gcr.io/overleaf-ops
--env-add=
--env-pass-through=
--esmock-loader=False
--is-library=True
--node-version=20.18.2
--public-repo=False
--script-version=4.7.0

6
libraries/object-persistor/index.js Normal file
View File

@@ -0,0 +1,6 @@
const PersistorFactory = require('./src/PersistorFactory')
module.exports = function ObjectPersistor(settings) {
return PersistorFactory(settings)
}
module.exports.Errors = require('./src/Errors')

45
libraries/object-persistor/package.json Normal file
View File

@@ -0,0 +1,45 @@
{
"name": "@overleaf/object-persistor",
"version": "1.0.2",
"description": "Module for storing objects in multiple backends, with fallback on 404 to assist migration between them",
"main": "index.js",
"scripts": {
"test": "npm run lint && npm run format && npm run types:check && npm run test:unit",
"test:unit": "mocha --exit test/**/*.{js,cjs}",
"lint": "eslint --ext .js --ext .cjs --ext .ts --max-warnings 0 --format unix .",
"lint:fix": "eslint --fix --ext .js --ext .cjs --ext .ts .",
"format": "prettier --list-different $PWD/'**/*.{js,cjs,ts}'",
"format:fix": "prettier --write $PWD/'**/*.{js,cjs,ts}'",
"test:ci": "npm run test:unit",
"types:check": "tsc --noEmit"
},
"repository": {
"type": "git",
"url": "github.com:overleaf/object-persistor"
},
"author": "Overleaf (https://www.overleaf.com/)",
"license": "AGPL-3.0",
"dependencies": {
"@google-cloud/storage": "^6.10.1",
"@overleaf/logger": "*",
"@overleaf/metrics": "*",
"@overleaf/o-error": "*",
"@overleaf/stream-utils": "*",
"aws-sdk": "^2.1691.0",
"fast-crc32c": "overleaf/node-fast-crc32c#aae6b2a4c7a7a159395df9cc6c38dfde702d6f51",
"glob": "^7.1.6",
"range-parser": "^1.2.1",
"tiny-async-pool": "^1.1.0"
},
"devDependencies": {
"chai": "^4.3.6",
"chai-as-promised": "^7.1.1",
"mocha": "^11.1.0",
"mock-fs": "^5.2.0",
"mongodb": "6.12.0",
"sandboxed-module": "^2.0.4",
"sinon": "^9.2.4",
"sinon-chai": "^3.7.0",
"typescript": "^5.0.4"
}
}

163
libraries/object-persistor/src/AbstractPersistor.js Normal file
View File

@@ -0,0 +1,163 @@
const { NotImplementedError } = require('./Errors')
module.exports = class AbstractPersistor {
/**
* @param location
* @param target
* @param {string} source
* @return {Promise<void>}
*/
async sendFile(location, target, source) {
throw new NotImplementedError('method not implemented in persistor', {
method: 'sendFile',
location,
target,
source,
})
}
/**
* @param location
* @param target
* @param {NodeJS.ReadableStream} sourceStream
* @param {Object} opts
* @return {Promise<void>}
*/
async sendStream(location, target, sourceStream, opts = {}) {
throw new NotImplementedError('method not implemented in persistor', {
method: 'sendStream',
location,
target,
opts,
})
}
/**
* @param location
* @param name
* @param {Object} [opts]
* @param {Number} [opts.start]
* @param {Number} [opts.end]
* @return {Promise<NodeJS.ReadableStream>}
*/
async getObjectStream(location, name, opts = {}) {
throw new NotImplementedError('method not implemented in persistor', {
method: 'getObjectStream',
location,
name,
opts,
})
}
/**
* @param {string} location
* @param {string} name
* @return {Promise<string>}
*/
async getRedirectUrl(location, name) {
throw new NotImplementedError('method not implemented in persistor', {
method: 'getRedirectUrl',
location,
name,
})
}
/**
* @param {string} location
* @param {string} name
* @param {Object} opts
* @return {Promise<number>}
*/
async getObjectSize(location, name, opts) {
throw new NotImplementedError('method not implemented in persistor', {
method: 'getObjectSize',
location,
name,
})
}
/**
* @param {string} location
* @param {string} name
* @param {Object} opts
* @return {Promise<string>}
*/
async getObjectMd5Hash(location, name, opts) {
throw new NotImplementedError('method not implemented in persistor', {
method: 'getObjectMd5Hash',
location,
name,
})
}
/**
* @param {string} location
* @param {string} fromName
* @param {string} toName
* @param {Object} opts
* @return {Promise<void>}
*/
async copyObject(location, fromName, toName, opts) {
throw new NotImplementedError('method not implemented in persistor', {
method: 'copyObject',
location,
fromName,
toName,
})
}
/**
* @param {string} location
* @param {string} name
* @return {Promise<void>}
*/
async deleteObject(location, name) {
throw new NotImplementedError('method not implemented in persistor', {
method: 'deleteObject',
location,
name,
})
}
/**
* @param {string} location
* @param {string} name
* @param {string} [continuationToken]
* @return {Promise<void>}
*/
async deleteDirectory(location, name, continuationToken) {
throw new NotImplementedError('method not implemented in persistor', {
method: 'deleteDirectory',
location,
name,
})
}
/**
* @param {string} location
* @param {string} name
* @param {Object} opts
* @return {Promise<boolean>}
*/
async checkIfObjectExists(location, name, opts) {
throw new NotImplementedError('method not implemented in persistor', {
method: 'checkIfObjectExists',
location,
name,
})
}
/**
* @param {string} location
* @param {string} name
* @param {string} [continuationToken]
* @return {Promise<number>}
*/
async directorySize(location, name, continuationToken) {
throw new NotImplementedError('method not implemented in persistor', {
method: 'directorySize',
location,
name,
})
}
}

19
libraries/object-persistor/src/Errors.js Normal file
View File

@@ -0,0 +1,19 @@
const OError = require('@overleaf/o-error')
class NotFoundError extends OError {}
class WriteError extends OError {}
class ReadError extends OError {}
class SettingsError extends OError {}
class NotImplementedError extends OError {}
class AlreadyWrittenError extends OError {}
class NoKEKMatchedError extends OError {}
module.exports = {
NotFoundError,
WriteError,
ReadError,
SettingsError,
NotImplementedError,
AlreadyWrittenError,
NoKEKMatchedError,
}

330
libraries/object-persistor/src/FSPersistor.js Normal file
View File

@@ -0,0 +1,330 @@
const crypto = require('node:crypto')
const fs = require('node:fs')
const fsPromises = require('node:fs/promises')
const globCallbacks = require('glob')
const Path = require('node:path')
const { PassThrough } = require('node:stream')
const { pipeline } = require('node:stream/promises')
const { promisify } = require('node:util')
const AbstractPersistor = require('./AbstractPersistor')
const { ReadError, WriteError, NotImplementedError } = require('./Errors')
const PersistorHelper = require('./PersistorHelper')
const glob = promisify(globCallbacks)
module.exports = class FSPersistor extends AbstractPersistor {
constructor(settings = {}) {
if (settings.storageClass) {
throw new NotImplementedError(
'FS backend does not support storage classes'
)
}
super()
this.useSubdirectories = Boolean(settings.useSubdirectories)
}
async sendFile(location, target, source) {
// actually copy the file (instead of moving it) to maintain consistent behaviour
// between the different implementations
try {
const sourceStream = fs.createReadStream(source)
await this.sendStream(location, target, sourceStream)
} catch (err) {
throw PersistorHelper.wrapError(
err,
'failed to copy the specified file',
{ location, target, source },
WriteError
)
}
}
async sendStream(location, target, sourceStream, opts = {}) {
if (opts.ifNoneMatch === '*') {
// The standard library only has fs.rename(), which does not support exclusive flags.
// Refuse to act on this write operation.
throw new NotImplementedError(
'Overwrite protection required by caller, but it is not available is FS backend. Configure GCS or S3 backend instead, get in touch with support for further information.'
)
}
const targetPath = this._getFsPath(location, target)
try {
await this._ensureDirectoryExists(targetPath)
const tempFilePath = await this._writeStreamToTempFile(
location,
sourceStream,
opts
)
try {
await fsPromises.rename(tempFilePath, targetPath)
} finally {
await this._cleanupTempFile(tempFilePath)
}
} catch (err) {
throw PersistorHelper.wrapError(
err,
'failed to write stream',
{ location, target, ifNoneMatch: opts.ifNoneMatch },
WriteError
)
}
}
// opts may be {start: Number, end: Number}
async getObjectStream(location, name, opts = {}) {
if (opts.autoGunzip) {
throw new NotImplementedError(
'opts.autoGunzip is not supported by FS backend. Configure GCS or S3 backend instead, get in touch with support for further information.'
)
}
const observer = new PersistorHelper.ObserverStream({
metric: 'fs.ingress', // ingress to us from disk
bucket: location,
})
const fsPath = this._getFsPath(location, name)
try {
opts.fd = await fsPromises.open(fsPath, 'r')
} catch (err) {
throw PersistorHelper.wrapError(
err,
'failed to open file for streaming',
{ location, name, fsPath, opts },
ReadError
)
}
const stream = fs.createReadStream(null, opts)
// Return a PassThrough stream with a minimal interface. It will buffer until the caller starts reading. It will emit errors from the source stream (Stream.pipeline passes errors along).
const pass = new PassThrough()
pipeline(stream, observer, pass).catch(() => {})
return pass
}
async getRedirectUrl() {
// not implemented
return null
}
async getObjectSize(location, filename) {
const fsPath = this._getFsPath(location, filename)
try {
const stat = await fsPromises.stat(fsPath)
return stat.size
} catch (err) {
throw PersistorHelper.wrapError(
err,
'failed to stat file',
{ location, filename },
ReadError
)
}
}
async getObjectMd5Hash(location, filename) {
const fsPath = this._getFsPath(location, filename)
try {
const stream = fs.createReadStream(fsPath)
const hash = await PersistorHelper.calculateStreamMd5(stream)
return hash
} catch (err) {
throw new ReadError(
'unable to get md5 hash from file',
{ location, filename },
err
)
}
}
async copyObject(location, source, target) {
const sourceFsPath = this._getFsPath(location, source)
const targetFsPath = this._getFsPath(location, target)
try {
await this._ensureDirectoryExists(targetFsPath)
await fsPromises.copyFile(sourceFsPath, targetFsPath)
} catch (err) {
throw PersistorHelper.wrapError(
err,
'failed to copy file',
{ location, source, target, sourceFsPath, targetFsPath },
WriteError
)
}
}
async deleteObject(location, name) {
const fsPath = this._getFsPath(location, name)
try {
// S3 doesn't give us a 404 when a file wasn't there to be deleted, so we
// should be consistent here as well
await fsPromises.rm(fsPath, { force: true })
} catch (err) {
throw PersistorHelper.wrapError(
err,
'failed to delete file',
{ location, name, fsPath },
WriteError
)
}
}
async deleteDirectory(location, name) {
const fsPath = this._getFsPath(location, name)
try {
if (this.useSubdirectories) {
await fsPromises.rm(fsPath, { recursive: true, force: true })
} else {
const files = await this._listDirectory(fsPath)
for (const file of files) {
await fsPromises.rm(file, { force: true })
}
}
} catch (err) {
throw PersistorHelper.wrapError(
err,
'failed to delete directory',
{ location, name, fsPath },
WriteError
)
}
}
async checkIfObjectExists(location, name) {
const fsPath = this._getFsPath(location, name)
try {
const stat = await fsPromises.stat(fsPath)
return !!stat
} catch (err) {
if (err.code === 'ENOENT') {
return false
}
throw PersistorHelper.wrapError(
err,
'failed to stat file',
{ location, name, fsPath },
ReadError
)
}
}
// note, does not recurse into subdirectories, as we use a flattened directory structure
async directorySize(location, name) {
const fsPath = this._getFsPath(location, name)
let size = 0
try {
const files = await this._listDirectory(fsPath)
for (const file of files) {
try {
const stat = await fsPromises.stat(file)
if (stat.isFile()) {
size += stat.size
}
} catch (err) {
// ignore files that may have just been deleted
if (err.code !== 'ENOENT') {
throw err
}
}
}
} catch (err) {
throw PersistorHelper.wrapError(
err,
'failed to get directory size',
{ location, name },
ReadError
)
}
return size
}
async _writeStreamToTempFile(location, stream, opts = {}) {
const observerOptions = {
metric: 'fs.egress', // egress from us to disk
bucket: location,
}
const observer = new PersistorHelper.ObserverStream(observerOptions)
const tempDirPath = await fsPromises.mkdtemp(Path.join(location, 'tmp-'))
const tempFilePath = Path.join(tempDirPath, 'uploaded-file')
const transforms = [observer]
let md5Observer
if (opts.sourceMd5) {
md5Observer = createMd5Observer()
transforms.push(md5Observer.transform)
}
try {
const writeStream = fs.createWriteStream(tempFilePath)
await pipeline(stream, ...transforms, writeStream)
} catch (err) {
await this._cleanupTempFile(tempFilePath)
throw new WriteError(
'problem writing temp file locally',
{ tempFilePath },
err
)
}
if (opts.sourceMd5) {
const actualMd5 = md5Observer.hash.digest('hex')
if (actualMd5 !== opts.sourceMd5) {
await this._cleanupTempFile(tempFilePath)
throw new WriteError('md5 hash mismatch', {
expectedMd5: opts.sourceMd5,
actualMd5,
})
}
}
return tempFilePath
}
async _cleanupTempFile(tempFilePath) {
const dirPath = Path.dirname(tempFilePath)
await fsPromises.rm(dirPath, { force: true, recursive: true })
}
_getFsPath(location, key) {
key = key.replace(/\/$/, '')
if (!this.useSubdirectories) {
key = key.replace(/\//g, '_')
}
return Path.join(location, key)
}
async _listDirectory(path) {
if (this.useSubdirectories) {
return await glob(Path.join(path, '**'))
} else {
return await glob(`${path}_*`)
}
}
async _ensureDirectoryExists(path) {
await fsPromises.mkdir(Path.dirname(path), { recursive: true })
}
}
function createMd5Observer() {
const hash = crypto.createHash('md5')
async function* transform(chunks) {
for await (const chunk of chunks) {
hash.update(chunk)
yield chunk
}
}
return { hash, transform }
}

354
libraries/object-persistor/src/GcsPersistor.js Normal file
View File

@@ -0,0 +1,354 @@
const fs = require('node:fs')
const { pipeline } = require('node:stream/promises')
const { PassThrough } = require('node:stream')
const { Storage, IdempotencyStrategy } = require('@google-cloud/storage')
const {
WriteError,
ReadError,
NotFoundError,
NotImplementedError,
} = require('./Errors')
const asyncPool = require('tiny-async-pool')
const AbstractPersistor = require('./AbstractPersistor')
const PersistorHelper = require('./PersistorHelper')
const Logger = require('@overleaf/logger')
const zlib = require('node:zlib')
module.exports = class GcsPersistor extends AbstractPersistor {
constructor(settings) {
if (settings.storageClass) {
throw new NotImplementedError(
'Use default bucket class for GCS instead of settings.storageClass'
)
}
super()
this.settings = settings
// endpoint settings will be null by default except for tests
// that's OK - GCS uses the locally-configured service account by default
const storageOptions = {}
if (this.settings.endpoint) {
storageOptions.projectId = this.settings.endpoint.projectId
storageOptions.apiEndpoint = this.settings.endpoint.apiEndpoint
}
storageOptions.retryOptions = { ...this.settings.retryOptions }
if (storageOptions.retryOptions) {
if (storageOptions.retryOptions.idempotencyStrategy) {
const value =
IdempotencyStrategy[this.settings.retryOptions.idempotencyStrategy]
if (value === undefined) {
throw new Error(
'Unrecognised value for retryOptions.idempotencyStrategy'
)
}
Logger.info(
`Setting retryOptions.idempotencyStrategy to ${storageOptions.retryOptions.idempotencyStrategy} (${value})`
)
storageOptions.retryOptions.idempotencyStrategy = value
}
}
this.storage = new Storage(storageOptions)
}
async sendFile(bucketName, key, fsPath) {
return await this.sendStream(bucketName, key, fs.createReadStream(fsPath))
}
async sendStream(bucketName, key, readStream, opts = {}) {
try {
const observeOptions = {
metric: 'gcs.egress', // egress from us to GCS
bucket: bucketName,
}
let sourceMd5 = opts.sourceMd5
if (!sourceMd5) {
// if there is no supplied md5 hash, we calculate the hash as the data passes through
observeOptions.hash = 'md5'
}
const observer = new PersistorHelper.ObserverStream(observeOptions)
const writeOptions = {
// disabling of resumable uploads is recommended by Google:
resumable: false,
}
if (sourceMd5) {
writeOptions.validation = 'md5'
writeOptions.metadata = writeOptions.metadata || {}
writeOptions.metadata.md5Hash = PersistorHelper.hexToBase64(sourceMd5)
}
if (opts.contentType) {
writeOptions.metadata = writeOptions.metadata || {}
writeOptions.metadata.contentType = opts.contentType
}
if (opts.contentEncoding) {
writeOptions.metadata = writeOptions.metadata || {}
writeOptions.metadata.contentEncoding = opts.contentEncoding
}
const fileOptions = {}
if (opts.ifNoneMatch === '*') {
fileOptions.generation = 0
}
const uploadStream = this.storage
.bucket(bucketName)
.file(key, fileOptions)
.createWriteStream(writeOptions)
await pipeline(readStream, observer, uploadStream)
// if we didn't have an md5 hash, we should compare our computed one with Google's
// as we couldn't tell GCS about it beforehand
if (!sourceMd5) {
sourceMd5 = observer.getHash()
// throws on mismatch
await PersistorHelper.verifyMd5(this, bucketName, key, sourceMd5)
}
} catch (err) {
throw PersistorHelper.wrapError(
err,
'upload to GCS failed',
{ bucketName, key, ifNoneMatch: opts.ifNoneMatch },
WriteError
)
}
}
async getObjectStream(bucketName, key, opts = {}) {
const observer = new PersistorHelper.ObserverStream({
metric: 'gcs.ingress', // ingress to us from GCS
bucket: bucketName,
})
const stream = this.storage
.bucket(bucketName)
.file(key)
.createReadStream({ decompress: false, ...opts })
let contentEncoding
try {
await new Promise((resolve, reject) => {
stream.on('response', res => {
switch (res.statusCode) {
case 200: // full response
case 206: // partial response
contentEncoding = res.headers['content-encoding']
return resolve()
case 404:
return reject(new NotFoundError())
default:
return reject(new Error('non success status: ' + res.statusCode))
}
})
stream.on('error', reject)
stream.read(0) // kick off request
})
} catch (err) {
throw PersistorHelper.wrapError(
err,
'error reading file from GCS',
{ bucketName, key, opts },
ReadError
)
}
// Return a PassThrough stream with a minimal interface. It will buffer until the caller starts reading. It will emit errors from the source stream (Stream.pipeline passes errors along).
const pass = new PassThrough()
const transformer = []
if (contentEncoding === 'gzip' && opts.autoGunzip) {
transformer.push(zlib.createGunzip())
}
pipeline(stream, observer, ...transformer, pass).catch(() => {})
return pass
}
async getRedirectUrl(bucketName, key) {
if (this.settings.unsignedUrls) {
// Construct a direct URL to the object download endpoint
// (see https://cloud.google.com/storage/docs/request-endpoints#json-api)
const apiEndpoint =
this.settings.endpoint.apiEndpoint || 'https://storage.googleapis.com'
return `${apiEndpoint}/download/storage/v1/b/${bucketName}/o/${key}?alt=media`
}
try {
const [url] = await this.storage
.bucket(bucketName)
.file(key)
.getSignedUrl({
action: 'read',
expires: Date.now() + this.settings.signedUrlExpiryInMs,
})
return url
} catch (err) {
throw PersistorHelper.wrapError(
err,
'error generating signed url for GCS file',
{ bucketName, key },
ReadError
)
}
}
async getObjectSize(bucketName, key) {
try {
const [metadata] = await this.storage
.bucket(bucketName)
.file(key)
.getMetadata()
return parseInt(metadata.size, 10)
} catch (err) {
throw PersistorHelper.wrapError(
err,
'error getting size of GCS object',
{ bucketName, key },
ReadError
)
}
}
async getObjectMd5Hash(bucketName, key) {
try {
const [metadata] = await this.storage
.bucket(bucketName)
.file(key)
.getMetadata()
return PersistorHelper.base64ToHex(metadata.md5Hash)
} catch (err) {
throw PersistorHelper.wrapError(
err,
'error getting hash of GCS object',
{ bucketName, key },
ReadError
)
}
}
async deleteObject(bucketName, key) {
try {
const file = this.storage.bucket(bucketName).file(key)
if (this.settings.deletedBucketSuffix) {
await file.copy(
this.storage
.bucket(`${bucketName}${this.settings.deletedBucketSuffix}`)
.file(`${key}-${new Date().toISOString()}`)
)
}
if (this.settings.unlockBeforeDelete) {
await file.setMetadata({ eventBasedHold: false })
}
await file.delete()
} catch (err) {
// ignore 404s: it's fine if the file doesn't exist.
if (err.code === 404) {
return
}
throw PersistorHelper.wrapError(
err,
'error deleting GCS object',
{ bucketName, key },
WriteError
)
}
}
async deleteDirectory(bucketName, key) {
const prefix = ensurePrefixIsDirectory(key)
let query = { prefix, autoPaginate: false }
do {
try {
const [files, nextQuery] = await this.storage
.bucket(bucketName)
.getFiles(query)
// iterate over paginated results using the nextQuery returned by getFiles
query = nextQuery
if (Array.isArray(files) && files.length > 0) {
await asyncPool(
this.settings.deleteConcurrency,
files,
async file => {
await this.deleteObject(bucketName, file.name)
}
)
}
} catch (err) {
const error = PersistorHelper.wrapError(
err,
'failed to delete directory in GCS',
{ bucketName, key },
WriteError
)
if (error instanceof NotFoundError) {
return
}
throw error
}
} while (query)
}
async directorySize(bucketName, key) {
let files
const prefix = ensurePrefixIsDirectory(key)
try {
const [response] = await this.storage
.bucket(bucketName)
.getFiles({ prefix })
files = response
} catch (err) {
throw PersistorHelper.wrapError(
err,
'failed to list objects in GCS',
{ bucketName, key },
ReadError
)
}
return files.reduce(
(acc, file) => parseInt(file.metadata.size, 10) + acc,
0
)
}
async checkIfObjectExists(bucketName, key) {
try {
const [response] = await this.storage
.bucket(bucketName)
.file(key)
.exists()
return response
} catch (err) {
throw PersistorHelper.wrapError(
err,
'error checking if file exists in GCS',
{ bucketName, key },
ReadError
)
}
}
async copyObject(bucketName, sourceKey, destKey) {
try {
const src = this.storage.bucket(bucketName).file(sourceKey)
const dest = this.storage.bucket(bucketName).file(destKey)
await src.copy(dest)
} catch (err) {
// fake-gcs-server has a bug that returns an invalid response when the file does not exist
if (err.message === 'Cannot parse response as JSON: not found\n') {
err.code = 404
}
throw PersistorHelper.wrapError(
err,
'failed to copy file in GCS',
{ bucketName, sourceKey, destKey },
WriteError
)
}
}
}
function ensurePrefixIsDirectory(key) {
return key === '' || key.endsWith('/') ? key : `${key}/`
}

267
libraries/object-persistor/src/MigrationPersistor.js Normal file
View File

@@ -0,0 +1,267 @@
const AbstractPersistor = require('./AbstractPersistor')
const Logger = require('@overleaf/logger')
const Metrics = require('@overleaf/metrics')
const Stream = require('node:stream')
const { pipeline } = require('node:stream/promises')
const { NotFoundError, WriteError } = require('./Errors')
// Persistor that wraps two other persistors. Talks to the 'primary' by default,
// but will fall back to an older persistor in the case of a not-found error.
// If `Settings.fallback.copyOnMiss` is set, this will copy files from the fallback
// to the primary, in the event that they are missing.
//
// It is unlikely that the bucket/location name will be the same on the fallback
// as the primary. The bucket names should be overridden in `Settings.fallback.buckets`
// e.g.
// Settings.fallback.buckets = {
// myBucketOnS3: 'myBucketOnGCS'
// }
module.exports = class MigrationPersistor extends AbstractPersistor {
/**
* @param {AbstractPersistor} primaryPersistor
* @param {AbstractPersistor} fallbackPersistor
* @param settings
*/
constructor(primaryPersistor, fallbackPersistor, settings) {
super()
/**
* @type {AbstractPersistor}
*/
this.primaryPersistor = primaryPersistor
/**
* @type {AbstractPersistor}
*/
this.fallbackPersistor = fallbackPersistor
this.settings = settings
}
async sendFile(...args) {
return await this.primaryPersistor.sendFile(...args)
}
async sendStream(...args) {
return await this.primaryPersistor.sendStream(...args)
}
async getRedirectUrl(...args) {
return await this.primaryPersistor.getRedirectUrl(...args)
}
async getObjectMd5Hash(...args) {
return await this._runWithFallback('getObjectMd5Hash', ...args)
}
async checkIfObjectExists(...args) {
return await this._runWithFallback('checkIfObjectExists', ...args)
}
async getObjectSize(...args) {
return await this._runWithFallback('getObjectSize', ...args)
}
async directorySize(...args) {
return await this._runWithFallback('directorySize', ...args)
}
async deleteObject(...args) {
return await this._runOnBoth('deleteObject', ...args)
}
async deleteDirectory(...args) {
return await this._runOnBoth('deleteDirectory', ...args)
}
async getObjectStream(bucket, key, opts = {}) {
const shouldCopy = this.settings.copyOnMiss && !opts.start && !opts.end
try {
return await this.primaryPersistor.getObjectStream(bucket, key, opts)
} catch (err) {
if (err instanceof NotFoundError) {
const fallbackBucket = this._getFallbackBucket(bucket)
const fallbackStream = await this.fallbackPersistor.getObjectStream(
fallbackBucket,
key,
opts
)
// tee the stream to the client, and as a copy to the primary (if necessary)
// start listening on both straight away so that we don't consume bytes
// in one place before the other
const returnStream = new Stream.PassThrough()
pipeline(fallbackStream, returnStream).catch(error => {
Logger.warn({ error }, 'failed to copy object from fallback')
})
if (shouldCopy) {
const copyStream = new Stream.PassThrough()
pipeline(fallbackStream, copyStream).catch(error => {
Logger.warn({ error }, 'failed to copy object from fallback')
})
this._copyStreamFromFallbackAndVerify(
copyStream,
fallbackBucket,
bucket,
key,
key
).catch(error => {
Logger.warn({ error }, 'failed to copy file from fallback')
})
}
return returnStream
}
throw err
}
}
async copyObject(bucket, sourceKey, destKey) {
try {
return await this.primaryPersistor.copyObject(bucket, sourceKey, destKey)
} catch (err) {
if (err instanceof NotFoundError) {
const fallbackBucket = this._getFallbackBucket(bucket)
const fallbackStream = await this.fallbackPersistor.getObjectStream(
fallbackBucket,
sourceKey,
{}
)
const copyStream = new Stream.PassThrough()
pipeline(fallbackStream, copyStream).catch(error => {
Logger.warn({ error }, 'failed to copy object from fallback')
})
if (this.settings.copyOnMiss) {
const missStream = new Stream.PassThrough()
pipeline(fallbackStream, missStream).catch(error => {
Logger.warn({ error }, 'failed to copy object from fallback')
})
// copy from sourceKey -> sourceKey
this._copyStreamFromFallbackAndVerify(
missStream,
fallbackBucket,
bucket,
sourceKey,
sourceKey
).catch(() => {
// swallow errors, as this runs in the background and will log a warning
})
}
// copy from sourceKey -> destKey
return await this._copyStreamFromFallbackAndVerify(
copyStream,
fallbackBucket,
bucket,
sourceKey,
destKey
)
}
throw err
}
}
async _copyStreamFromFallbackAndVerify(
stream,
sourceBucket,
destBucket,
sourceKey,
destKey
) {
try {
let sourceMd5
try {
sourceMd5 = await this.fallbackPersistor.getObjectMd5Hash(
sourceBucket,
sourceKey
)
} catch (err) {
Logger.warn(err, 'error getting md5 hash from fallback persistor')
}
await this.primaryPersistor.sendStream(destBucket, destKey, stream, {
sourceMd5,
})
} catch (err) {
const error = new WriteError(
'unable to copy file to destination persistor',
{
sourceBucket,
destBucket,
sourceKey,
destKey,
},
err
)
Metrics.inc('fallback.copy.failure')
try {
await this.primaryPersistor.deleteObject(destBucket, destKey)
} catch (err) {
error.info.cleanupError = new WriteError(
'unable to clean up destination copy artifact',
{
destBucket,
destKey,
},
err
)
}
throw error
}
}
_getFallbackBucket(bucket) {
return (this.settings.buckets && this.settings.buckets[bucket]) || bucket
}
async _runOnBoth(methodName, bucket, ...moreArgs) {
const fallbackBucket = this._getFallbackBucket(bucket)
await Promise.all([
this.primaryPersistor[methodName](bucket, ...moreArgs),
this.fallbackPersistor[methodName](fallbackBucket, ...moreArgs),
])
}
/**
* @param {keyof AbstractPersistor} methodName
* @param bucket
* @param key
* @param moreArgs
*/
async _runWithFallback(methodName, bucket, key, ...moreArgs) {
try {
return await this.primaryPersistor[methodName](bucket, key, ...moreArgs)
} catch (err) {
if (err instanceof NotFoundError) {
const fallbackBucket = this._getFallbackBucket(bucket)
if (this.settings.copyOnMiss) {
const fallbackStream = await this.fallbackPersistor.getObjectStream(
fallbackBucket,
key,
{}
)
// run in background
this._copyStreamFromFallbackAndVerify(
fallbackStream,
fallbackBucket,
bucket,
key,
key
).catch(err => {
Logger.warn({ err }, 'failed to copy file from fallback')
})
}
return await this.fallbackPersistor[methodName](
fallbackBucket,
key,
...moreArgs
)
}
throw err
}
}
}

469
libraries/object-persistor/src/PerProjectEncryptedS3Persistor.js Normal file
View File

@@ -0,0 +1,469 @@
// @ts-check
const Crypto = require('node:crypto')
const Stream = require('node:stream')
const fs = require('node:fs')
const { promisify } = require('node:util')
const { WritableBuffer } = require('@overleaf/stream-utils')
const { S3Persistor, SSECOptions } = require('./S3Persistor.js')
const {
AlreadyWrittenError,
NoKEKMatchedError,
NotFoundError,
NotImplementedError,
ReadError,
} = require('./Errors')
const logger = require('@overleaf/logger')
const Path = require('node:path')
const generateKey = promisify(Crypto.generateKey)
const hkdf = promisify(Crypto.hkdf)
const AES256_KEY_LENGTH = 32
/**
* @typedef {import('aws-sdk').AWSError} AWSError
*/
/**
* @typedef {Object} Settings
* @property {boolean} automaticallyRotateDEKEncryption
* @property {string} dataEncryptionKeyBucketName
* @property {boolean} ignoreErrorsFromDEKReEncryption
* @property {(bucketName: string, path: string) => string} pathToProjectFolder
* @property {() => Promise<Array<RootKeyEncryptionKey>>} getRootKeyEncryptionKeys
*/
/**
* Helper function to make TS happy when accessing error properties
* AWSError is not an actual class, so we cannot use instanceof.
* @param {any} err
* @return {err is AWSError}
*/
function isAWSError(err) {
return !!err
}
/**
* @param {any} err
* @return {boolean}
*/
function isForbiddenError(err) {
if (!err || !(err instanceof ReadError || err instanceof NotFoundError)) {
return false
}
const cause = err.cause
if (!isAWSError(cause)) return false
return cause.statusCode === 403
}
class RootKeyEncryptionKey {
/** @type {Buffer} */
#keyEncryptionKey
/** @type {Buffer} */
#salt
/**
* @param {Buffer} keyEncryptionKey
* @param {Buffer} salt
*/
constructor(keyEncryptionKey, salt) {
if (keyEncryptionKey.byteLength !== AES256_KEY_LENGTH) {
throw new Error(`kek is not ${AES256_KEY_LENGTH} bytes long`)
}
this.#keyEncryptionKey = keyEncryptionKey
this.#salt = salt
}
/**
* @param {string} prefix
* @return {Promise<SSECOptions>}
*/
async forProject(prefix) {
return new SSECOptions(
Buffer.from(
await hkdf(
'sha256',
this.#keyEncryptionKey,
this.#salt,
prefix,
AES256_KEY_LENGTH
)
)
)
}
}
class PerProjectEncryptedS3Persistor extends S3Persistor {
/** @type {Settings} */
#settings
/** @type {Promise<Array<RootKeyEncryptionKey>>} */
#availableKeyEncryptionKeysPromise
/**
* @param {Settings} settings
*/
constructor(settings) {
if (!settings.dataEncryptionKeyBucketName) {
throw new Error('settings.dataEncryptionKeyBucketName is missing')
}
super(settings)
this.#settings = settings
this.#availableKeyEncryptionKeysPromise = settings
.getRootKeyEncryptionKeys()
.then(rootKEKs => {
if (rootKEKs.length === 0) throw new Error('no root kek provided')
return rootKEKs
})
}
async ensureKeyEncryptionKeysLoaded() {
await this.#availableKeyEncryptionKeysPromise
}
/**
* @param {string} bucketName
* @param {string} path
* @return {{dekPath: string, projectFolder: string}}
*/
#buildProjectPaths(bucketName, path) {
const projectFolder = this.#settings.pathToProjectFolder(bucketName, path)
const dekPath = Path.join(projectFolder, 'dek')
return { projectFolder, dekPath }
}
/**
* @param {string} projectFolder
* @return {Promise<SSECOptions>}
*/
async #getCurrentKeyEncryptionKey(projectFolder) {
const [currentRootKEK] = await this.#availableKeyEncryptionKeysPromise
return await currentRootKEK.forProject(projectFolder)
}
/**
* @param {string} bucketName
* @param {string} path
*/
async getDataEncryptionKeySize(bucketName, path) {
const { projectFolder, dekPath } = this.#buildProjectPaths(bucketName, path)
for (const rootKEK of await this.#availableKeyEncryptionKeysPromise) {
const ssecOptions = await rootKEK.forProject(projectFolder)
try {
return await super.getObjectSize(
this.#settings.dataEncryptionKeyBucketName,
dekPath,
{ ssecOptions }
)
} catch (err) {
if (isForbiddenError(err)) continue
throw err
}
}
throw new NoKEKMatchedError('no kek matched')
}
/**
* @param {string} bucketName
* @param {string} path
* @return {Promise<CachedPerProjectEncryptedS3Persistor>}
*/
async forProject(bucketName, path) {
return new CachedPerProjectEncryptedS3Persistor(
this,
await this.#getDataEncryptionKeyOptions(bucketName, path)
)
}
/**
* @param {string} bucketName
* @param {string} path
* @return {Promise<CachedPerProjectEncryptedS3Persistor>}
*/
async forProjectRO(bucketName, path) {
return new CachedPerProjectEncryptedS3Persistor(
this,
await this.#getExistingDataEncryptionKeyOptions(bucketName, path)
)
}
/**
* @param {string} bucketName
* @param {string} path
* @return {Promise<CachedPerProjectEncryptedS3Persistor>}
*/
async generateDataEncryptionKey(bucketName, path) {
return new CachedPerProjectEncryptedS3Persistor(
this,
await this.#generateDataEncryptionKeyOptions(bucketName, path)
)
}
/**
* @param {string} bucketName
* @param {string} path
* @return {Promise<SSECOptions>}
*/
async #generateDataEncryptionKeyOptions(bucketName, path) {
const dataEncryptionKey = (
await generateKey('aes', { length: 256 })
).export()
const { projectFolder, dekPath } = this.#buildProjectPaths(bucketName, path)
await super.sendStream(
this.#settings.dataEncryptionKeyBucketName,
dekPath,
Stream.Readable.from([dataEncryptionKey]),
{
// Do not overwrite any objects if already created
ifNoneMatch: '*',
ssecOptions: await this.#getCurrentKeyEncryptionKey(projectFolder),
contentLength: 32,
}
)
return new SSECOptions(dataEncryptionKey)
}
/**
* @param {string} bucketName
* @param {string} path
* @return {Promise<SSECOptions>}
*/
async #getExistingDataEncryptionKeyOptions(bucketName, path) {
const { projectFolder, dekPath } = this.#buildProjectPaths(bucketName, path)
let res
let kekIndex = 0
for (const rootKEK of await this.#availableKeyEncryptionKeysPromise) {
const ssecOptions = await rootKEK.forProject(projectFolder)
try {
res = await super.getObjectStream(
this.#settings.dataEncryptionKeyBucketName,
dekPath,
{ ssecOptions }
)
break
} catch (err) {
if (isForbiddenError(err)) {
kekIndex++
continue
}
throw err
}
}
if (!res) throw new NoKEKMatchedError('no kek matched')
const buf = new WritableBuffer()
await Stream.promises.pipeline(res, buf)
if (kekIndex !== 0 && this.#settings.automaticallyRotateDEKEncryption) {
const ssecOptions = await this.#getCurrentKeyEncryptionKey(projectFolder)
try {
await super.sendStream(
this.#settings.dataEncryptionKeyBucketName,
dekPath,
Stream.Readable.from([buf.getContents()]),
{ ssecOptions }
)
} catch (err) {
if (this.#settings.ignoreErrorsFromDEKReEncryption) {
logger.warn({ err, dekPath }, 'failed to persist re-encrypted DEK')
} else {
throw err
}
}
}
return new SSECOptions(buf.getContents())
}
/**
* @param {string} bucketName
* @param {string} path
* @return {Promise<SSECOptions>}
*/
async #getDataEncryptionKeyOptions(bucketName, path) {
try {
return await this.#getExistingDataEncryptionKeyOptions(bucketName, path)
} catch (err) {
if (err instanceof NotFoundError) {
try {
return await this.#generateDataEncryptionKeyOptions(bucketName, path)
} catch (err2) {
if (err2 instanceof AlreadyWrittenError) {
// Concurrent initial write
return await this.#getExistingDataEncryptionKeyOptions(
bucketName,
path
)
}
throw err2
}
}
throw err
}
}
async sendStream(bucketName, path, sourceStream, opts = {}) {
const ssecOptions =
opts.ssecOptions ||
(await this.#getDataEncryptionKeyOptions(bucketName, path))
return await super.sendStream(bucketName, path, sourceStream, {
...opts,
ssecOptions,
})
}
async getObjectStream(bucketName, path, opts = {}) {
const ssecOptions =
opts.ssecOptions ||
(await this.#getExistingDataEncryptionKeyOptions(bucketName, path))
return await super.getObjectStream(bucketName, path, {
...opts,
ssecOptions,
})
}
async getObjectSize(bucketName, path, opts = {}) {
const ssecOptions =
opts.ssecOptions ||
(await this.#getExistingDataEncryptionKeyOptions(bucketName, path))
return await super.getObjectSize(bucketName, path, { ...opts, ssecOptions })
}
async getObjectStorageClass(bucketName, path, opts = {}) {
const ssecOptions =
opts.ssecOptions ||
(await this.#getExistingDataEncryptionKeyOptions(bucketName, path))
return await super.getObjectStorageClass(bucketName, path, {
...opts,
ssecOptions,
})
}
async directorySize(bucketName, path, continuationToken) {
// Note: Listing a bucket does not require SSE-C credentials.
return await super.directorySize(bucketName, path, continuationToken)
}
async deleteDirectory(bucketName, path, continuationToken) {
// Let [Settings.pathToProjectFolder] validate the project path before deleting things.
const { projectFolder, dekPath } = this.#buildProjectPaths(bucketName, path)
// Note: Listing/Deleting a prefix does not require SSE-C credentials.
await super.deleteDirectory(bucketName, path, continuationToken)
if (projectFolder === path) {
await super.deleteObject(
this.#settings.dataEncryptionKeyBucketName,
dekPath
)
}
}
async getObjectMd5Hash(bucketName, path, opts = {}) {
// The ETag in object metadata is not the MD5 content hash, skip the HEAD request.
opts = { ...opts, etagIsNotMD5: true }
return await super.getObjectMd5Hash(bucketName, path, opts)
}
async copyObject(bucketName, sourcePath, destinationPath, opts = {}) {
const ssecOptions =
opts.ssecOptions ||
(await this.#getDataEncryptionKeyOptions(bucketName, destinationPath))
const ssecSrcOptions =
opts.ssecSrcOptions ||
(await this.#getExistingDataEncryptionKeyOptions(bucketName, sourcePath))
return await super.copyObject(bucketName, sourcePath, destinationPath, {
...opts,
ssecOptions,
ssecSrcOptions,
})
}
/**
* @param {string} bucketName
* @param {string} path
* @return {Promise<string>}
*/
async getRedirectUrl(bucketName, path) {
throw new NotImplementedError('signed links are not supported with SSE-C')
}
}
/**
* Helper class for batch updates to avoid repeated fetching of the project path.
*
* A general "cache" for project keys is another alternative. For now, use a helper class.
*/
class CachedPerProjectEncryptedS3Persistor {
/** @type SSECOptions */
#projectKeyOptions
/** @type PerProjectEncryptedS3Persistor */
#parent
/**
* @param {PerProjectEncryptedS3Persistor} parent
* @param {SSECOptions} projectKeyOptions
*/
constructor(parent, projectKeyOptions) {
this.#parent = parent
this.#projectKeyOptions = projectKeyOptions
}
/**
* @param {string} bucketName
* @param {string} path
* @param {string} fsPath
*/
async sendFile(bucketName, path, fsPath) {
return await this.sendStream(bucketName, path, fs.createReadStream(fsPath))
}
/**
*
* @param {string} bucketName
* @param {string} path
* @return {Promise<number>}
*/
async getObjectSize(bucketName, path) {
return await this.#parent.getObjectSize(bucketName, path)
}
/**
* @param {string} bucketName
* @param {string} path
* @param {NodeJS.ReadableStream} sourceStream
* @param {Object} opts
* @param {string} [opts.contentType]
* @param {string} [opts.contentEncoding]
* @param {number} [opts.contentLength]
* @param {'*'} [opts.ifNoneMatch]
* @param {SSECOptions} [opts.ssecOptions]
* @param {string} [opts.sourceMd5]
* @return {Promise<void>}
*/
async sendStream(bucketName, path, sourceStream, opts = {}) {
return await this.#parent.sendStream(bucketName, path, sourceStream, {
...opts,
ssecOptions: this.#projectKeyOptions,
})
}
/**
* @param {string} bucketName
* @param {string} path
* @param {Object} opts
* @param {number} [opts.start]
* @param {number} [opts.end]
* @param {boolean} [opts.autoGunzip]
* @param {SSECOptions} [opts.ssecOptions]
* @return {Promise<NodeJS.ReadableStream>}
*/
async getObjectStream(bucketName, path, opts = {}) {
return await this.#parent.getObjectStream(bucketName, path, {
...opts,
ssecOptions: this.#projectKeyOptions,
})
}
}
module.exports = {
PerProjectEncryptedS3Persistor,
CachedPerProjectEncryptedS3Persistor,
RootKeyEncryptionKey,
}

51
libraries/object-persistor/src/PersistorFactory.js Normal file
View File

@@ -0,0 +1,51 @@
const Logger = require('@overleaf/logger')
const { SettingsError } = require('./Errors')
const GcsPersistor = require('./GcsPersistor')
const { S3Persistor } = require('./S3Persistor')
const FSPersistor = require('./FSPersistor')
const MigrationPersistor = require('./MigrationPersistor')
const {
PerProjectEncryptedS3Persistor,
} = require('./PerProjectEncryptedS3Persistor')
function getPersistor(backend, settings) {
switch (backend) {
case 'aws-sdk':
case 's3':
return new S3Persistor(settings.s3)
case 's3SSEC':
return new PerProjectEncryptedS3Persistor(settings.s3SSEC)
case 'fs':
return new FSPersistor({
useSubdirectories: settings.useSubdirectories,
paths: settings.paths,
})
case 'gcs':
return new GcsPersistor(settings.gcs)
default:
throw new SettingsError('unknown backend', { backend })
}
}
module.exports = function create(settings) {
Logger.info(
{
backend: settings.backend,
fallback: settings.fallback && settings.fallback.backend,
},
'Loading backend'
)
if (!settings.backend) {
throw new SettingsError('no backend specified - config incomplete')
}
let persistor = getPersistor(settings.backend, settings)
if (settings.fallback && settings.fallback.backend) {
const primary = persistor
const fallback = getPersistor(settings.fallback.backend, settings)
persistor = new MigrationPersistor(primary, fallback, settings.fallback)
}
return persistor
}

173
libraries/object-persistor/src/PersistorHelper.js Normal file
View File

@@ -0,0 +1,173 @@
const Crypto = require('node:crypto')
const Stream = require('node:stream')
const { pipeline } = require('node:stream/promises')
const Logger = require('@overleaf/logger')
const Metrics = require('@overleaf/metrics')
const { WriteError, NotFoundError, AlreadyWrittenError } = require('./Errors')
const _128KiB = 128 * 1024
const TIMING_BUCKETS = [
0, 1, 2, 5, 10, 20, 50, 100, 200, 500, 1000, 2000, 5000, 10000, 20000, 50000,
]
const SIZE_BUCKETS = [
0,
1_000,
10_000,
100_000,
_128KiB,
1_000_000,
10_000_000,
50_000_000,
100_000_000,
]
/**
* Observes data that passes through and optionally computes hash for content.
*/
class ObserverStream extends Stream.Transform {
/**
* @param {Object} opts
* @param {string} opts.metric prefix for metrics
* @param {string} opts.bucket name of source/target bucket
* @param {string} [opts.hash] optional hash algorithm, e.g. 'md5'
*/
constructor(opts) {
super({ autoDestroy: true })
const { metric, bucket, hash = '' } = opts
this.bytes = 0
this.start = performance.now()
if (hash) {
this.hash = Crypto.createHash(hash)
}
const onEnd = status => {
const size = this.bytes < _128KiB ? 'lt-128KiB' : 'gte-128KiB'
const labels = { size, bucket, status }
// Keep this counter metric to allow rendering long-term charts.
Metrics.count(metric, this.bytes, 1, labels)
Metrics.inc(`${metric}.hit`, 1, labels)
if (status === 'error') return
// The below metrics are only relevant for successfully fetched objects.
Metrics.histogram(`${metric}.size`, this.bytes, SIZE_BUCKETS, {
status,
bucket,
})
if (this.firstByteAfterMs) {
Metrics.histogram(
`${metric}.latency.first-byte`,
this.firstByteAfterMs,
TIMING_BUCKETS,
labels
)
}
Metrics.histogram(
`${metric}.latency`,
this.#getMsSinceStart(),
TIMING_BUCKETS,
labels
)
}
this.once('error', () => onEnd('error'))
this.once('end', () => onEnd('success'))
}
#getMsSinceStart() {
return performance.now() - this.start
}
_transform(chunk, encoding, done) {
if (this.bytes === 0) {
this.firstByteAfterMs = this.#getMsSinceStart()
}
if (this.hash) {
this.hash.update(chunk)
}
this.bytes += chunk.length
this.push(chunk)
done()
}
getHash() {
return this.hash && this.hash.digest('hex')
}
}
module.exports = {
ObserverStream,
calculateStreamMd5,
verifyMd5,
wrapError,
hexToBase64,
base64ToHex,
}
// returns a promise which resolves with the md5 hash of the stream
// - consumes the stream
async function calculateStreamMd5(stream) {
const hash = Crypto.createHash('md5')
hash.setEncoding('hex')
await pipeline(stream, hash)
return hash.read()
}
// verifies the md5 hash of a file against the supplied md5 or the one stored in
// storage if not supplied - deletes the new file if the md5 does not match and
// throws an error
async function verifyMd5(persistor, bucket, key, sourceMd5, destMd5 = null) {
if (!destMd5) {
destMd5 = await persistor.getObjectMd5Hash(bucket, key)
}
if (sourceMd5 !== destMd5) {
try {
await persistor.deleteObject(bucket, key)
} catch (err) {
Logger.warn(err, 'error deleting file for invalid upload')
}
throw new WriteError('source and destination hashes do not match', {
sourceMd5,
destMd5,
bucket,
key,
})
}
}
function wrapError(error, message, params, ErrorType) {
params = {
...params,
cause: error,
}
if (
error instanceof NotFoundError ||
['NoSuchKey', 'NotFound', 404, 'AccessDenied', 'ENOENT'].includes(
error.code
) ||
(error.response && error.response.statusCode === 404)
) {
return new NotFoundError('no such file', params, error)
} else if (
params.ifNoneMatch === '*' &&
(error.code === 'PreconditionFailed' ||
error.response?.statusCode === 412 ||
error instanceof AlreadyWrittenError)
) {
return new AlreadyWrittenError(message, params, error)
} else {
return new ErrorType(message, params, error)
}
}
function base64ToHex(base64) {
return Buffer.from(base64, 'base64').toString('hex')
}
function hexToBase64(hex) {
return Buffer.from(hex, 'hex').toString('base64')
}

617
libraries/object-persistor/src/S3Persistor.js Normal file
View File

@@ -0,0 +1,617 @@
// @ts-check
const http = require('node:http')
const https = require('node:https')
if (http.globalAgent.maxSockets < 300) {
http.globalAgent.maxSockets = 300
}
if (https.globalAgent.maxSockets < 300) {
https.globalAgent.maxSockets = 300
}
const Crypto = require('node:crypto')
const Metrics = require('@overleaf/metrics')
const AbstractPersistor = require('./AbstractPersistor')
const PersistorHelper = require('./PersistorHelper')
const { pipeline, PassThrough } = require('node:stream')
const fs = require('node:fs')
const S3 = require('aws-sdk/clients/s3')
const { URL } = require('node:url')
const { WriteError, ReadError, NotFoundError } = require('./Errors')
const zlib = require('node:zlib')
/**
* Wrapper with private fields to avoid revealing them on console, JSON.stringify or similar.
*/
class SSECOptions {
#keyAsBuffer
#keyMD5
/**
* @param {Buffer} keyAsBuffer
*/
constructor(keyAsBuffer) {
this.#keyAsBuffer = keyAsBuffer
this.#keyMD5 = Crypto.createHash('md5').update(keyAsBuffer).digest('base64')
}
getPutOptions() {
return {
SSECustomerKey: this.#keyAsBuffer,
SSECustomerKeyMD5: this.#keyMD5,
SSECustomerAlgorithm: 'AES256',
}
}
getGetOptions() {
return {
SSECustomerKey: this.#keyAsBuffer,
SSECustomerKeyMD5: this.#keyMD5,
SSECustomerAlgorithm: 'AES256',
}
}
getCopyOptions() {
return {
CopySourceSSECustomerKey: this.#keyAsBuffer,
CopySourceSSECustomerKeyMD5: this.#keyMD5,
CopySourceSSECustomerAlgorithm: 'AES256',
}
}
}
class S3Persistor extends AbstractPersistor {
/** @type {Map<string, S3>} */
#clients = new Map()
constructor(settings = {}) {
super()
settings.storageClass = settings.storageClass || {}
this.settings = settings
}
/**
* @param {string} bucketName
* @param {string} key
* @param {string} fsPath
* @return {Promise<void>}
*/
async sendFile(bucketName, key, fsPath) {
await this.sendStream(bucketName, key, fs.createReadStream(fsPath))
}
/**
* @param {string} bucketName
* @param {string} key
* @param {NodeJS.ReadableStream} readStream
* @param {Object} opts
* @param {string} [opts.contentType]
* @param {string} [opts.contentEncoding]
* @param {number} [opts.contentLength]
* @param {'*'} [opts.ifNoneMatch]
* @param {SSECOptions} [opts.ssecOptions]
* @param {string} [opts.sourceMd5]
* @return {Promise<void>}
*/
async sendStream(bucketName, key, readStream, opts = {}) {
try {
const observeOptions = {
metric: 's3.egress', // egress from us to S3
bucket: bucketName,
}
const observer = new PersistorHelper.ObserverStream(observeOptions)
// observer will catch errors, clean up and log a warning
pipeline(readStream, observer, () => {})
/** @type {S3.PutObjectRequest} */
const uploadOptions = {
Bucket: bucketName,
Key: key,
Body: observer,
}
if (this.settings.storageClass[bucketName]) {
uploadOptions.StorageClass = this.settings.storageClass[bucketName]
}
if (opts.contentType) {
uploadOptions.ContentType = opts.contentType
}
if (opts.contentEncoding) {
uploadOptions.ContentEncoding = opts.contentEncoding
}
if (opts.contentLength) {
uploadOptions.ContentLength = opts.contentLength
}
if (opts.ifNoneMatch === '*') {
uploadOptions.IfNoneMatch = '*'
}
if (opts.ssecOptions) {
Object.assign(uploadOptions, opts.ssecOptions.getPutOptions())
}
// if we have an md5 hash, pass this to S3 to verify the upload - otherwise
// we rely on the S3 client's checksum calculation to validate the upload
let computeChecksums = false
if (opts.sourceMd5) {
uploadOptions.ContentMD5 = PersistorHelper.hexToBase64(opts.sourceMd5)
} else {
computeChecksums = true
}
if (this.settings.disableMultiPartUpload) {
await this._getClientForBucket(bucketName, computeChecksums)
.putObject(uploadOptions)
.promise()
} else {
await this._getClientForBucket(bucketName, computeChecksums)
.upload(uploadOptions, { partSize: this.settings.partSize })
.promise()
}
} catch (err) {
throw PersistorHelper.wrapError(
err,
'upload to S3 failed',
{ bucketName, key, ifNoneMatch: opts.ifNoneMatch },
WriteError
)
}
}
/**
* @param {string} bucketName
* @param {string} key
* @param {Object} [opts]
* @param {number} [opts.start]
* @param {number} [opts.end]
* @param {boolean} [opts.autoGunzip]
* @param {SSECOptions} [opts.ssecOptions]
* @return {Promise<NodeJS.ReadableStream>}
*/
async getObjectStream(bucketName, key, opts) {
opts = opts || {}
const params = {
Bucket: bucketName,
Key: key,
}
if (opts.start != null && opts.end != null) {
params.Range = `bytes=${opts.start}-${opts.end}`
}
if (opts.ssecOptions) {
Object.assign(params, opts.ssecOptions.getGetOptions())
}
const observer = new PersistorHelper.ObserverStream({
metric: 's3.ingress', // ingress from S3 to us
bucket: bucketName,
})
const req = this._getClientForBucket(bucketName).getObject(params)
const stream = req.createReadStream()
let contentEncoding
try {
await new Promise((resolve, reject) => {
req.on('httpHeaders', (statusCode, headers) => {
switch (statusCode) {
case 200: // full response
case 206: // partial response
contentEncoding = headers['content-encoding']
return resolve(undefined)
case 403: // AccessDenied
return // handled by stream.on('error') handler below
case 404: // NoSuchKey
return reject(new NotFoundError('not found'))
default:
// handled by stream.on('error') handler below
}
})
// The AWS SDK is forwarding any errors from the request to the stream.
// The AWS SDK is emitting additional errors on the stream ahead of starting to stream.
stream.on('error', reject)
// The AWS SDK is kicking off the request in the next event loop cycle.
})
} catch (err) {
throw PersistorHelper.wrapError(
err,
'error reading file from S3',
{ bucketName, key, opts },
ReadError
)
}
// Return a PassThrough stream with a minimal interface. It will buffer until the caller starts reading. It will emit errors from the source stream (Stream.pipeline passes errors along).
const pass = new PassThrough()
const transformer = []
if (contentEncoding === 'gzip' && opts.autoGunzip) {
transformer.push(zlib.createGunzip())
}
pipeline(stream, observer, ...transformer, pass, err => {
if (err) req.abort()
})
return pass
}
/**
* @param {string} bucketName
* @param {string} key
* @return {Promise<string>}
*/
async getRedirectUrl(bucketName, key) {
const expiresSeconds = Math.round(this.settings.signedUrlExpiryInMs / 1000)
try {
return await this._getClientForBucket(bucketName).getSignedUrlPromise(
'getObject',
{
Bucket: bucketName,
Key: key,
Expires: expiresSeconds,
}
)
} catch (err) {
throw PersistorHelper.wrapError(
err,
'error generating signed url for S3 file',
{ bucketName, key },
ReadError
)
}
}
/**
* @param {string} bucketName
* @param {string} key
* @param {string} [continuationToken]
* @return {Promise<void>}
*/
async deleteDirectory(bucketName, key, continuationToken) {
let response
const options = { Bucket: bucketName, Prefix: key }
if (continuationToken) {
options.ContinuationToken = continuationToken
}
try {
response = await this._getClientForBucket(bucketName)
.listObjectsV2(options)
.promise()
} catch (err) {
throw PersistorHelper.wrapError(
err,
'failed to list objects in S3',
{ bucketName, key },
ReadError
)
}
const objects = response.Contents?.map(item => ({ Key: item.Key || '' }))
if (objects?.length) {
try {
await this._getClientForBucket(bucketName)
.deleteObjects({
Bucket: bucketName,
Delete: {
Objects: objects,
Quiet: true,
},
})
.promise()
} catch (err) {
throw PersistorHelper.wrapError(
err,
'failed to delete objects in S3',
{ bucketName, key },
WriteError
)
}
}
if (response.IsTruncated) {
await this.deleteDirectory(
bucketName,
key,
response.NextContinuationToken
)
}
}
/**
* @param {string} bucketName
* @param {string} key
* @param {Object} opts
* @param {SSECOptions} [opts.ssecOptions]
* @return {Promise<S3.HeadObjectOutput>}
*/
async #headObject(bucketName, key, opts = {}) {
const params = { Bucket: bucketName, Key: key }
if (opts.ssecOptions) {
Object.assign(params, opts.ssecOptions.getGetOptions())
}
try {
return await this._getClientForBucket(bucketName)
.headObject(params)
.promise()
} catch (err) {
throw PersistorHelper.wrapError(
err,
'error getting size of s3 object',
{ bucketName, key },
ReadError
)
}
}
/**
* @param {string} bucketName
* @param {string} key
* @param {Object} opts
* @param {SSECOptions} [opts.ssecOptions]
* @return {Promise<number>}
*/
async getObjectSize(bucketName, key, opts = {}) {
const response = await this.#headObject(bucketName, key, opts)
return response.ContentLength || 0
}
/**
* @param {string} bucketName
* @param {string} key
* @param {Object} opts
* @param {SSECOptions} [opts.ssecOptions]
* @return {Promise<string | undefined>}
*/
async getObjectStorageClass(bucketName, key, opts = {}) {
const response = await this.#headObject(bucketName, key, opts)
return response.StorageClass
}
/**
* @param {string} bucketName
* @param {string} key
* @param {Object} opts
* @param {SSECOptions} [opts.ssecOptions]
* @param {boolean} [opts.etagIsNotMD5]
* @return {Promise<string>}
*/
async getObjectMd5Hash(bucketName, key, opts = {}) {
try {
if (!opts.etagIsNotMD5) {
const response = await this.#headObject(bucketName, key, opts)
const md5 = S3Persistor._md5FromResponse(response)
if (md5) {
return md5
}
}
// etag is not in md5 format
Metrics.inc('s3.md5Download')
return await PersistorHelper.calculateStreamMd5(
await this.getObjectStream(bucketName, key, opts)
)
} catch (err) {
throw PersistorHelper.wrapError(
err,
'error getting hash of s3 object',
{ bucketName, key },
ReadError
)
}
}
/**
* @param {string} bucketName
* @param {string} key
* @return {Promise<void>}
*/
async deleteObject(bucketName, key) {
try {
await this._getClientForBucket(bucketName)
.deleteObject({ Bucket: bucketName, Key: key })
.promise()
} catch (err) {
// s3 does not give us a NotFoundError here
throw PersistorHelper.wrapError(
err,
'failed to delete file in S3',
{ bucketName, key },
WriteError
)
}
}
/**
* @param {string} bucketName
* @param {string} sourceKey
* @param {string} destKey
* @param {Object} opts
* @param {SSECOptions} [opts.ssecSrcOptions]
* @param {SSECOptions} [opts.ssecOptions]
* @return {Promise<void>}
*/
async copyObject(bucketName, sourceKey, destKey, opts = {}) {
const params = {
Bucket: bucketName,
Key: destKey,
CopySource: `${bucketName}/${sourceKey}`,
}
if (opts.ssecSrcOptions) {
Object.assign(params, opts.ssecSrcOptions.getCopyOptions())
}
if (opts.ssecOptions) {
Object.assign(params, opts.ssecOptions.getPutOptions())
}
try {
await this._getClientForBucket(bucketName).copyObject(params).promise()
} catch (err) {
throw PersistorHelper.wrapError(
err,
'failed to copy file in S3',
params,
WriteError
)
}
}
/**
* @param {string} bucketName
* @param {string} key
* @param {Object} opts
* @param {SSECOptions} [opts.ssecOptions]
* @return {Promise<boolean>}
*/
async checkIfObjectExists(bucketName, key, opts) {
try {
await this.getObjectSize(bucketName, key, opts)
return true
} catch (err) {
if (err instanceof NotFoundError) {
return false
}
throw PersistorHelper.wrapError(
err,
'error checking whether S3 object exists',
{ bucketName, key },
ReadError
)
}
}
/**
* @param {string} bucketName
* @param {string} key
* @param {string} [continuationToken]
* @return {Promise<number>}
*/
async directorySize(bucketName, key, continuationToken) {
try {
const options = {
Bucket: bucketName,
Prefix: key,
}
if (continuationToken) {
options.ContinuationToken = continuationToken
}
const response = await this._getClientForBucket(bucketName)
.listObjectsV2(options)
.promise()
const size =
response.Contents?.reduce((acc, item) => (item.Size || 0) + acc, 0) || 0
if (response.IsTruncated) {
return (
size +
(await this.directorySize(
bucketName,
key,
response.NextContinuationToken
))
)
}
return size
} catch (err) {
throw PersistorHelper.wrapError(
err,
'error getting directory size in S3',
{ bucketName, key },
ReadError
)
}
}
/**
* @param {string} bucket
* @param {boolean} computeChecksums
* @return {S3}
* @private
*/
_getClientForBucket(bucket, computeChecksums = false) {
/** @type {S3.Types.ClientConfiguration} */
const clientOptions = {}
const cacheKey = `${bucket}:${computeChecksums}`
if (computeChecksums) {
clientOptions.computeChecksums = true
}
let client = this.#clients.get(cacheKey)
if (!client) {
client = new S3(
this._buildClientOptions(
this.settings.bucketCreds?.[bucket],
clientOptions
)
)
this.#clients.set(cacheKey, client)
}
return client
}
/**
* @param {Object} bucketCredentials
* @param {S3.Types.ClientConfiguration} clientOptions
* @return {S3.Types.ClientConfiguration}
* @private
*/
_buildClientOptions(bucketCredentials, clientOptions) {
const options = clientOptions || {}
if (bucketCredentials) {
options.credentials = {
accessKeyId: bucketCredentials.auth_key,
secretAccessKey: bucketCredentials.auth_secret,
}
} else if (this.settings.key) {
options.credentials = {
accessKeyId: this.settings.key,
secretAccessKey: this.settings.secret,
}
} else {
// Use the default credentials provider (process.env -> SSP -> ini -> IAM)
// Docs: https://docs.aws.amazon.com/AWSJavaScriptSDK/latest/AWS/CredentialProviderChain.html#defaultProviders-property
}
if (this.settings.endpoint) {
const endpoint = new URL(this.settings.endpoint)
options.endpoint = this.settings.endpoint
options.sslEnabled = endpoint.protocol === 'https:'
}
// path-style access is only used for acceptance tests
if (this.settings.pathStyle) {
options.s3ForcePathStyle = true
}
for (const opt of ['httpOptions', 'maxRetries', 'region']) {
if (this.settings[opt]) {
options[opt] = this.settings[opt]
}
}
if (options.sslEnabled && this.settings.ca && !options.httpOptions?.agent) {
options.httpOptions = options.httpOptions || {}
options.httpOptions.agent = new https.Agent({
rejectUnauthorized: true,
ca: this.settings.ca,
})
}
return options
}
/**
* @param {S3.HeadObjectOutput} response
* @return {string|null}
* @private
*/
static _md5FromResponse(response) {
const md5 = (response.ETag || '').replace(/[ "]/g, '')
if (!md5.match(/^[a-f0-9]{32}$/)) {
return null
}
return md5
}
}
module.exports = {
S3Persistor,
SSECOptions,
}

33
libraries/object-persistor/test/Init.js Normal file
View File

@@ -0,0 +1,33 @@
const SandboxedModule = require('sandboxed-module')
const chai = require('chai')
const sinon = require('sinon')
chai.use(require('sinon-chai'))
chai.use(require('chai-as-promised'))
SandboxedModule.configure({
requires: {
'@overleaf/logger': {
debug() {},
log() {},
info() {},
warn() {},
error() {},
err() {},
},
'@overleaf/metrics': {
inc: sinon.stub(),
count: sinon.stub(),
histogram: sinon.stub(),
Timer: class Timer {
done() {}
},
},
},
globals: { Buffer, Math, console, process, URL },
sourceTransformers: {
removeNodePrefix: function (source) {
return source.replace(/require\(['"]node:/g, "require('")
},
},
})

417
libraries/object-persistor/test/unit/FSPersistorTests.js Normal file
View File

@@ -0,0 +1,417 @@
const crypto = require('node:crypto')
const { expect } = require('chai')
const mockFs = require('mock-fs')
const fs = require('node:fs')
const fsPromises = require('node:fs/promises')
const Path = require('node:path')
const StreamPromises = require('node:stream/promises')
const SandboxedModule = require('sandboxed-module')
const Errors = require('../../src/Errors')
const MODULE_PATH = '../../src/FSPersistor.js'
describe('FSPersistorTests', function () {
const localFiles = {
'/uploads/info.txt': Buffer.from('This information is critical', {
encoding: 'utf-8',
}),
'/uploads/other.txt': Buffer.from('Some other content', {
encoding: 'utf-8',
}),
}
const location = '/bucket'
const files = {
wombat: 'animals/wombat.tex',
giraffe: 'animals/giraffe.tex',
potato: 'vegetables/potato.tex',
}
const scenarios = [
{
description: 'default settings',
settings: {},
fsPath: key => Path.join(location, key.replaceAll('/', '_')),
},
{
description: 'with useSubdirectories = true',
settings: { useSubdirectories: true },
fsPath: key => Path.join(location, key),
},
]
for (const scenario of scenarios) {
describe(scenario.description, function () {
let persistor
beforeEach(function () {
const FSPersistor = SandboxedModule.require(MODULE_PATH, {
requires: {
'fs/promises': fsPromises,
'stream/promises': StreamPromises,
'./Errors': Errors,
},
})
persistor = new FSPersistor(scenario.settings)
})
beforeEach(function () {
mockFs({
...localFiles,
'/not-a-dir':
'This regular file is meant to prevent using this path as a directory',
'/directory/subdirectory': {},
})
})
afterEach(function () {
mockFs.restore()
})
describe('sendFile', function () {
it('should copy the file', async function () {
await persistor.sendFile(location, files.wombat, '/uploads/info.txt')
const contents = await fsPromises.readFile(
scenario.fsPath(files.wombat)
)
expect(contents.equals(localFiles['/uploads/info.txt'])).to.be.true
})
it('should return an error if the file cannot be stored', async function () {
await expect(
persistor.sendFile('/not-a-dir', files.wombat, '/uploads/info.txt')
).to.be.rejectedWith(Errors.WriteError)
})
})
describe('sendStream', function () {
let stream
describe("when the file doesn't exist", function () {
beforeEach(function () {
stream = fs.createReadStream('/uploads/info.txt')
})
it('should write the stream to disk', async function () {
await persistor.sendStream(location, files.wombat, stream)
const contents = await fsPromises.readFile(
scenario.fsPath(files.wombat)
)
expect(contents.equals(localFiles['/uploads/info.txt'])).to.be.true
})
it('should delete the temporary file', async function () {
await persistor.sendStream(location, files.wombat, stream)
const entries = await fsPromises.readdir(location)
const tempDirs = entries.filter(dir => dir.startsWith('tmp-'))
expect(tempDirs).to.be.empty
})
describe('on error', function () {
beforeEach(async function () {
await expect(
persistor.sendStream('/not-a-dir', files.wombat, stream)
).to.be.rejectedWith(Errors.WriteError)
})
it('should not write the target file', async function () {
await expect(fsPromises.access(scenario.fsPath(files.wombat))).to
.be.rejected
})
it('should delete the temporary file', async function () {
await persistor.sendStream(location, files.wombat, stream)
const entries = await fsPromises.readdir(location)
const tempDirs = entries.filter(dir => dir.startsWith('tmp-'))
expect(tempDirs).to.be.empty
})
})
describe('when the md5 hash matches', function () {
it('should write the stream to disk', async function () {
await persistor.sendStream(location, files.wombat, stream, {
sourceMd5: md5(localFiles['/uploads/info.txt']),
})
const contents = await fsPromises.readFile(
scenario.fsPath(files.wombat)
)
expect(contents.equals(localFiles['/uploads/info.txt'])).to.be
.true
})
})
describe('when the md5 hash does not match', function () {
beforeEach(async function () {
await expect(
persistor.sendStream(location, files.wombat, stream, {
sourceMd5: md5('wrong content'),
})
).to.be.rejectedWith(Errors.WriteError)
})
it('should not write the target file', async function () {
await expect(fsPromises.access(scenario.fsPath(files.wombat))).to
.be.rejected
})
it('should delete the temporary file', async function () {
await persistor.sendStream(location, files.wombat, stream)
const entries = await fsPromises.readdir(location)
const tempDirs = entries.filter(dir => dir.startsWith('tmp-'))
expect(tempDirs).to.be.empty
})
})
})
describe('when the file already exists', function () {
let stream
beforeEach(async function () {
await persistor.sendFile(
location,
files.wombat,
'/uploads/info.txt'
)
stream = fs.createReadStream('/uploads/other.txt')
})
it('should write the stream to disk', async function () {
await persistor.sendStream(location, files.wombat, stream)
const contents = await fsPromises.readFile(
scenario.fsPath(files.wombat)
)
expect(contents.equals(localFiles['/uploads/other.txt'])).to.be.true
})
it('should delete the temporary file', async function () {
await persistor.sendStream(location, files.wombat, stream)
const entries = await fsPromises.readdir(location)
const tempDirs = entries.filter(dir => dir.startsWith('tmp-'))
expect(tempDirs).to.be.empty
})
describe('on error', function () {
beforeEach(async function () {
await expect(
persistor.sendStream('/not-a-dir', files.wombat, stream)
).to.be.rejectedWith(Errors.WriteError)
})
it('should not update the target file', async function () {
const contents = await fsPromises.readFile(
scenario.fsPath(files.wombat)
)
expect(contents.equals(localFiles['/uploads/info.txt'])).to.be
.true
})
it('should delete the temporary file', async function () {
await persistor.sendStream(location, files.wombat, stream)
const entries = await fsPromises.readdir(location)
const tempDirs = entries.filter(dir => dir.startsWith('tmp-'))
expect(tempDirs).to.be.empty
})
})
describe('when the md5 hash matches', function () {
it('should write the stream to disk', async function () {
await persistor.sendStream(location, files.wombat, stream, {
sourceMd5: md5(localFiles['/uploads/other.txt']),
})
const contents = await fsPromises.readFile(
scenario.fsPath(files.wombat)
)
expect(contents.equals(localFiles['/uploads/other.txt'])).to.be
.true
})
})
describe('when the md5 hash does not match', function () {
beforeEach(async function () {
await expect(
persistor.sendStream(location, files.wombat, stream, {
sourceMd5: md5('wrong content'),
})
).to.be.rejectedWith(Errors.WriteError)
})
it('should not update the target file', async function () {
const contents = await fsPromises.readFile(
scenario.fsPath(files.wombat)
)
expect(contents.equals(localFiles['/uploads/info.txt'])).to.be
.true
})
it('should delete the temporary file', async function () {
await persistor.sendStream(location, files.wombat, stream)
const entries = await fsPromises.readdir(location)
const tempDirs = entries.filter(dir => dir.startsWith('tmp-'))
expect(tempDirs).to.be.empty
})
})
})
})
describe('getObjectStream', function () {
beforeEach(async function () {
await persistor.sendFile(location, files.wombat, '/uploads/info.txt')
})
it('should return a string with the object contents', async function () {
const stream = await persistor.getObjectStream(location, files.wombat)
const contents = await streamToBuffer(stream)
expect(contents.equals(localFiles['/uploads/info.txt'])).to.be.true
})
it('should support ranges', async function () {
const stream = await persistor.getObjectStream(
location,
files.wombat,
{
start: 5,
end: 16,
}
)
const contents = await streamToBuffer(stream)
// end is inclusive in ranges, but exclusive in slice()
expect(contents.equals(localFiles['/uploads/info.txt'].slice(5, 17)))
.to.be.true
})
it('should give a NotFoundError if the file does not exist', async function () {
await expect(
persistor.getObjectStream(location, 'does-not-exist')
).to.be.rejectedWith(Errors.NotFoundError)
})
})
describe('getObjectSize', function () {
beforeEach(async function () {
await persistor.sendFile(location, files.wombat, '/uploads/info.txt')
})
it('should return the file size', async function () {
expect(
await persistor.getObjectSize(location, files.wombat)
).to.equal(localFiles['/uploads/info.txt'].length)
})
it('should throw a NotFoundError if the file does not exist', async function () {
await expect(
persistor.getObjectSize(location, 'does-not-exist')
).to.be.rejectedWith(Errors.NotFoundError)
})
})
describe('copyObject', function () {
beforeEach(async function () {
await persistor.sendFile(location, files.wombat, '/uploads/info.txt')
})
it('Should copy the file to the new location', async function () {
await persistor.copyObject(location, files.wombat, files.potato)
const contents = await fsPromises.readFile(
scenario.fsPath(files.potato)
)
expect(contents.equals(localFiles['/uploads/info.txt'])).to.be.true
})
})
describe('deleteObject', function () {
beforeEach(async function () {
await persistor.sendFile(location, files.wombat, '/uploads/info.txt')
await fsPromises.access(scenario.fsPath(files.wombat))
})
it('should delete the file', async function () {
await persistor.deleteObject(location, files.wombat)
await expect(fsPromises.access(scenario.fsPath(files.wombat))).to.be
.rejected
})
it("should ignore files that don't exist", async function () {
await persistor.deleteObject(location, 'does-not-exist')
})
})
describe('deleteDirectory', function () {
beforeEach(async function () {
for (const file of Object.values(files)) {
await persistor.sendFile(location, file, '/uploads/info.txt')
await fsPromises.access(scenario.fsPath(file))
}
})
it('should delete all files under the directory', async function () {
await persistor.deleteDirectory(location, 'animals')
for (const file of [files.wombat, files.giraffe]) {
await expect(fsPromises.access(scenario.fsPath(file))).to.be
.rejected
}
})
it('should not delete files under other directoris', async function () {
await persistor.deleteDirectory(location, 'animals')
await fsPromises.access(scenario.fsPath(files.potato))
})
it("should ignore directories that don't exist", async function () {
await persistor.deleteDirectory(location, 'does-not-exist')
for (const file of Object.values(files)) {
await fsPromises.access(scenario.fsPath(file))
}
})
})
describe('checkIfObjectExists', function () {
beforeEach(async function () {
await persistor.sendFile(location, files.wombat, '/uploads/info.txt')
})
it('should return true for existing files', async function () {
expect(
await persistor.checkIfObjectExists(location, files.wombat)
).to.equal(true)
})
it('should return false for non-existing files', async function () {
expect(
await persistor.checkIfObjectExists(location, 'does-not-exist')
).to.equal(false)
})
})
describe('directorySize', function () {
beforeEach(async function () {
for (const file of Object.values(files)) {
await persistor.sendFile(location, file, '/uploads/info.txt')
}
})
it('should sum directory files size', async function () {
expect(await persistor.directorySize(location, 'animals')).to.equal(
2 * localFiles['/uploads/info.txt'].length
)
})
it('should return 0 on non-existing directories', async function () {
expect(
await persistor.directorySize(location, 'does-not-exist')
).to.equal(0)
})
})
})
}
})
function md5(str) {
return crypto.createHash('md5').update(str).digest('hex')
}
async function streamToBuffer(stream) {
const chunks = []
for await (const chunk of stream) {
chunks.push(chunk)
}
return Buffer.concat(chunks)
}

726
libraries/object-persistor/test/unit/GcsPersistorTests.js Normal file
View File

@@ -0,0 +1,726 @@
const { EventEmitter } = require('node:events')
const sinon = require('sinon')
const chai = require('chai')
const { expect } = chai
const modulePath = '../../src/GcsPersistor.js'
const SandboxedModule = require('sandboxed-module')
const { ObjectId } = require('mongodb')
const asyncPool = require('tiny-async-pool')
const Errors = require('../../src/Errors')
describe('GcsPersistorTests', function () {
const filename = '/wombat/potato.tex'
const bucket = 'womBucket'
const key = 'monKey'
const destKey = 'donKey'
const genericError = new Error('guru meditation error')
const filesSize = 33
const md5 = 'ffffffff00000000ffffffff00000000'
const WriteStream = 'writeStream'
const redirectUrl = 'https://wombat.potato/giraffe'
let Logger,
Transform,
PassThrough,
Storage,
Fs,
GcsNotFoundError,
ReadStream,
Stream,
StreamPromises,
GcsBucket,
GcsFile,
GcsPersistor,
FileNotFoundError,
Hash,
Settings,
crypto,
files
beforeEach(function () {
Settings = {
directoryKeyRegex: /^[0-9a-fA-F]{24}\/[0-9a-fA-F]{24}/,
}
files = [
{
metadata: { size: '11', md5Hash: '/////wAAAAD/////AAAAAA==' },
delete: sinon.stub(),
},
{
metadata: { size: '22', md5Hash: '/////wAAAAD/////AAAAAA==' },
delete: sinon.stub(),
},
]
class FakeGCSResponse extends EventEmitter {
constructor() {
super()
this.statusCode = 200
this.err = null
}
read() {
if (this.err) return this.emit('error', this.err)
this.emit('response', { statusCode: this.statusCode, headers: {} })
}
}
ReadStream = new FakeGCSResponse()
PassThrough = class {}
Transform = class {
once() {}
}
Stream = {
PassThrough,
Transform,
}
StreamPromises = {
pipeline: sinon.stub().resolves(),
}
GcsFile = {
delete: sinon.stub().resolves(),
createReadStream: sinon.stub().returns(ReadStream),
getMetadata: sinon.stub().resolves([files[0].metadata]),
createWriteStream: sinon.stub().returns(WriteStream),
copy: sinon.stub().resolves(),
exists: sinon.stub().resolves([true]),
getSignedUrl: sinon.stub().resolves([redirectUrl]),
}
GcsBucket = {
file: sinon.stub().returns(GcsFile),
getFiles: sinon.stub().resolves([files]),
}
Storage = class {
constructor() {
this.interceptors = []
}
}
Storage.prototype.bucket = sinon.stub().returns(GcsBucket)
GcsNotFoundError = new Error('File not found')
GcsNotFoundError.code = 404
Fs = {
createReadStream: sinon.stub().returns(ReadStream),
}
FileNotFoundError = new Error('File not found')
FileNotFoundError.code = 'ENOENT'
Hash = {
end: sinon.stub(),
read: sinon.stub().returns(md5),
digest: sinon.stub().returns(md5),
setEncoding: sinon.stub(),
}
crypto = {
createHash: sinon.stub().returns(Hash),
}
Logger = {
warn: sinon.stub(),
}
GcsPersistor = new (SandboxedModule.require(modulePath, {
requires: {
'@google-cloud/storage': { Storage },
'@overleaf/logger': Logger,
'tiny-async-pool': asyncPool,
'./Errors': Errors,
fs: Fs,
stream: Stream,
'stream/promises': StreamPromises,
crypto,
},
globals: { console, Buffer },
}))(Settings)
})
describe('getObjectStream', function () {
describe('when called with valid parameters', function () {
let stream
beforeEach(async function () {
stream = await GcsPersistor.getObjectStream(bucket, key)
})
it('returns a PassThrough stream', function () {
expect(stream).to.be.instanceOf(PassThrough)
})
it('fetches the right key from the right bucket', function () {
expect(Storage.prototype.bucket).to.have.been.calledWith(bucket)
expect(GcsBucket.file).to.have.been.calledWith(key)
expect(GcsFile.createReadStream).to.have.been.called
})
it('disables automatic decompression', function () {
expect(GcsFile.createReadStream).to.have.been.calledWith({
decompress: false,
})
})
it('pipes the stream through the meter', function () {
expect(StreamPromises.pipeline).to.have.been.calledWith(
ReadStream,
sinon.match.instanceOf(Transform),
sinon.match.instanceOf(PassThrough)
)
})
})
describe('when called with a byte range', function () {
let stream
beforeEach(async function () {
stream = await GcsPersistor.getObjectStream(bucket, key, {
start: 5,
end: 10,
})
})
it('returns a PassThrough stream', function () {
expect(stream).to.be.instanceOf(PassThrough)
})
it('passes the byte range on to GCS', function () {
expect(GcsFile.createReadStream).to.have.been.calledWith({
decompress: false,
start: 5,
end: 10,
})
})
})
describe("when the file doesn't exist", function () {
let error, stream
beforeEach(async function () {
ReadStream.statusCode = 404
try {
stream = await GcsPersistor.getObjectStream(bucket, key)
} catch (e) {
error = e
}
})
it('does not return a stream', function () {
expect(stream).not.to.exist
})
it('throws a NotFoundError', function () {
expect(error).to.be.an.instanceOf(Errors.NotFoundError)
})
it('wraps the error', function () {
expect(error.cause).to.exist
})
it('stores the bucket and key in the error', function () {
expect(error.info).to.include({ bucketName: bucket, key })
})
})
describe('when Gcs encounters an unknown error', function () {
let error, stream
beforeEach(async function () {
ReadStream.err = genericError
try {
stream = await GcsPersistor.getObjectStream(bucket, key)
} catch (err) {
error = err
}
})
it('does not return a stream', function () {
expect(stream).not.to.exist
})
it('throws a ReadError', function () {
expect(error).to.be.an.instanceOf(Errors.ReadError)
})
it('wraps the error', function () {
expect(error.cause).to.exist
})
it('stores the bucket and key in the error', function () {
expect(error.info).to.include({ bucketName: bucket, key })
})
})
})
describe('getRedirectUrl', function () {
let signedUrl
describe('with signed URLs', function () {
beforeEach(async function () {
signedUrl = await GcsPersistor.getRedirectUrl(bucket, key)
})
it('should request a signed URL', function () {
expect(GcsFile.getSignedUrl).to.have.been.called
})
it('should return the url', function () {
expect(signedUrl).to.equal(redirectUrl)
})
})
describe('with unsigned URLs', function () {
beforeEach(async function () {
GcsPersistor.settings.unsignedUrls = true
GcsPersistor.settings.endpoint = {
apiEndpoint: 'http://custom.endpoint',
}
signedUrl = await GcsPersistor.getRedirectUrl(bucket, key)
})
it('should return a plain URL', function () {
expect(signedUrl).to.equal(
`http://custom.endpoint/download/storage/v1/b/${bucket}/o/${key}?alt=media`
)
})
})
})
describe('getObjectSize', function () {
describe('when called with valid parameters', function () {
let size
beforeEach(async function () {
size = await GcsPersistor.getObjectSize(bucket, key)
})
it('should return the object size', function () {
expect(size).to.equal(11)
})
it('should pass the bucket and key to GCS', function () {
expect(Storage.prototype.bucket).to.have.been.calledWith(bucket)
expect(GcsBucket.file).to.have.been.calledWith(key)
expect(GcsFile.getMetadata).to.have.been.called
})
})
describe('when the object is not found', function () {
let error
beforeEach(async function () {
GcsFile.getMetadata = sinon.stub().rejects(GcsNotFoundError)
try {
await GcsPersistor.getObjectSize(bucket, key)
} catch (err) {
error = err
}
})
it('should return a NotFoundError', function () {
expect(error).to.be.an.instanceOf(Errors.NotFoundError)
})
it('should wrap the error', function () {
expect(error.cause).to.equal(GcsNotFoundError)
})
})
describe('when GCS returns an error', function () {
let error
beforeEach(async function () {
GcsFile.getMetadata = sinon.stub().rejects(genericError)
try {
await GcsPersistor.getObjectSize(bucket, key)
} catch (err) {
error = err
}
})
it('should return a ReadError', function () {
expect(error).to.be.an.instanceOf(Errors.ReadError)
})
it('should wrap the error', function () {
expect(error.cause).to.equal(genericError)
})
})
})
describe('sendStream', function () {
describe('with valid parameters', function () {
beforeEach(async function () {
return GcsPersistor.sendStream(bucket, key, ReadStream)
})
it('should upload the stream', function () {
expect(Storage.prototype.bucket).to.have.been.calledWith(bucket)
expect(GcsBucket.file).to.have.been.calledWith(key)
expect(GcsFile.createWriteStream).to.have.been.called
})
it('should not try to create a resumable upload', function () {
expect(GcsFile.createWriteStream).to.have.been.calledWith({
resumable: false,
})
})
it('should meter the stream and pass it to GCS', function () {
expect(StreamPromises.pipeline).to.have.been.calledWith(
ReadStream,
sinon.match.instanceOf(Transform),
WriteStream
)
})
it('calculates the md5 hash of the file', function () {
expect(Hash.digest).to.have.been.called
})
})
describe('when a hash is supplied', function () {
beforeEach(async function () {
return GcsPersistor.sendStream(bucket, key, ReadStream, {
sourceMd5: 'aaaaaaaabbbbbbbbaaaaaaaabbbbbbbb',
})
})
it('should not calculate the md5 hash of the file', function () {
expect(Hash.digest).not.to.have.been.called
})
it('sends the hash in base64', function () {
expect(GcsFile.createWriteStream).to.have.been.calledWith({
validation: 'md5',
metadata: {
md5Hash: 'qqqqqru7u7uqqqqqu7u7uw==',
},
resumable: false,
})
})
it('does not fetch the md5 hash of the uploaded file', function () {
expect(GcsFile.getMetadata).not.to.have.been.called
})
})
describe('when metadata is supplied', function () {
const contentType = 'text/csv'
const contentEncoding = 'gzip'
beforeEach(async function () {
return GcsPersistor.sendStream(bucket, key, ReadStream, {
contentType,
contentEncoding,
})
})
it('should send the metadata to GCS', function () {
expect(GcsFile.createWriteStream).to.have.been.calledWith({
metadata: { contentType, contentEncoding },
resumable: false,
})
})
})
describe('when the upload fails', function () {
let error
beforeEach(async function () {
StreamPromises.pipeline
.withArgs(ReadStream, sinon.match.instanceOf(Transform), WriteStream)
.rejects(genericError)
try {
await GcsPersistor.sendStream(bucket, key, ReadStream)
} catch (err) {
error = err
}
})
it('throws a WriteError', function () {
expect(error).to.be.an.instanceOf(Errors.WriteError)
})
it('wraps the error', function () {
expect(error.cause).to.equal(genericError)
})
})
})
describe('sendFile', function () {
describe('with valid parameters', function () {
beforeEach(async function () {
return GcsPersistor.sendFile(bucket, key, filename)
})
it('should create a read stream for the file', function () {
expect(Fs.createReadStream).to.have.been.calledWith(filename)
})
it('should create a write stream', function () {
expect(Storage.prototype.bucket).to.have.been.calledWith(bucket)
expect(GcsBucket.file).to.have.been.calledWith(key)
expect(GcsFile.createWriteStream).to.have.been.called
})
it('should upload the stream via the meter', function () {
expect(StreamPromises.pipeline).to.have.been.calledWith(
ReadStream,
sinon.match.instanceOf(Transform),
WriteStream
)
})
})
})
describe('copyObject', function () {
const destinationFile = 'destFile'
beforeEach(function () {
GcsBucket.file.withArgs(destKey).returns(destinationFile)
})
describe('with valid parameters', function () {
beforeEach(async function () {
return GcsPersistor.copyObject(bucket, key, destKey)
})
it('should copy the object', function () {
expect(Storage.prototype.bucket).to.have.been.calledWith(bucket)
expect(GcsBucket.file).to.have.been.calledWith(key)
expect(GcsFile.copy).to.have.been.calledWith(destinationFile)
})
})
describe('when the file does not exist', function () {
let error
beforeEach(async function () {
GcsFile.copy = sinon.stub().rejects(GcsNotFoundError)
try {
await GcsPersistor.copyObject(bucket, key, destKey)
} catch (err) {
error = err
}
})
it('should throw a NotFoundError', function () {
expect(error).to.be.an.instanceOf(Errors.NotFoundError)
})
})
})
describe('deleteObject', function () {
describe('with valid parameters', function () {
beforeEach(async function () {
return GcsPersistor.deleteObject(bucket, key)
})
it('should delete the object', function () {
expect(Storage.prototype.bucket).to.have.been.calledWith(bucket)
expect(GcsBucket.file).to.have.been.calledWith(key)
expect(GcsFile.delete).to.have.been.called
})
})
describe('when the file does not exist', function () {
let error
beforeEach(async function () {
GcsFile.delete = sinon.stub().rejects(GcsNotFoundError)
try {
await GcsPersistor.deleteObject(bucket, key)
} catch (err) {
error = err
}
})
it('should not throw an error', function () {
expect(error).not.to.exist
})
})
})
describe('deleteDirectory', function () {
const directoryName = `${new ObjectId()}/${new ObjectId()}`
const directoryPrefix = `${directoryName}/`
describe('with valid parameters', function () {
beforeEach(async function () {
GcsBucket.getFiles = sinon.stub()
// set up multiple paginated calls to getFiles
GcsBucket.getFiles
.withArgs({ prefix: directoryPrefix, autoPaginate: false })
.resolves([['aaa', 'bbb'], 'call-1'])
GcsBucket.getFiles
.withArgs('call-1')
.resolves([['ccc', 'ddd', 'eee'], 'call-2'])
GcsBucket.getFiles.withArgs('call-2').resolves([['fff', 'ggg']])
return GcsPersistor.deleteDirectory(bucket, directoryName)
})
it('should list the objects in the directory', function () {
expect(Storage.prototype.bucket).to.have.been.calledWith(bucket)
expect(GcsBucket.getFiles).to.have.been.calledWith({
prefix: directoryPrefix,
autoPaginate: false,
})
expect(GcsBucket.getFiles).to.have.been.calledWith('call-1')
expect(GcsBucket.getFiles).to.have.been.calledWith('call-2')
})
it('should delete the files', function () {
expect(GcsFile.delete.callCount).to.equal(7)
})
})
describe('when there is an error listing the objects', function () {
let error
beforeEach(async function () {
GcsBucket.getFiles = sinon.stub().rejects(genericError)
try {
await GcsPersistor.deleteDirectory(bucket, directoryName)
} catch (err) {
error = err
}
})
it('should generate a WriteError', function () {
expect(error).to.be.an.instanceOf(Errors.WriteError)
})
it('should wrap the error', function () {
expect(error.cause).to.equal(genericError)
})
})
})
describe('directorySize', function () {
describe('with valid parameters', function () {
let size
beforeEach(async function () {
size = await GcsPersistor.directorySize(bucket, key)
})
it('should list the objects in the directory', function () {
expect(Storage.prototype.bucket).to.have.been.calledWith(bucket)
expect(GcsBucket.getFiles).to.have.been.calledWith({
prefix: `${key}/`,
})
})
it('should return the directory size', function () {
expect(size).to.equal(filesSize)
})
})
describe('when there are no files', function () {
let size
beforeEach(async function () {
GcsBucket.getFiles.resolves([[]])
size = await GcsPersistor.directorySize(bucket, key)
})
it('should list the objects in the directory', function () {
expect(Storage.prototype.bucket).to.have.been.calledWith(bucket)
expect(GcsBucket.getFiles).to.have.been.calledWith({
prefix: `${key}/`,
})
})
it('should return zero', function () {
expect(size).to.equal(0)
})
})
describe('when there is an error listing the objects', function () {
let error
beforeEach(async function () {
GcsBucket.getFiles.rejects(genericError)
try {
await GcsPersistor.directorySize(bucket, key)
} catch (err) {
error = err
}
})
it('should generate a ReadError', function () {
expect(error).to.be.an.instanceOf(Errors.ReadError)
})
it('should wrap the error', function () {
expect(error.cause).to.equal(genericError)
})
})
})
describe('checkIfObjectExists', function () {
describe('when the file exists', function () {
let exists
beforeEach(async function () {
exists = await GcsPersistor.checkIfObjectExists(bucket, key)
})
it('should ask the file if it exists', function () {
expect(Storage.prototype.bucket).to.have.been.calledWith(bucket)
expect(GcsBucket.file).to.have.been.calledWith(key)
expect(GcsFile.exists).to.have.been.called
})
it('should return that the file exists', function () {
expect(exists).to.equal(true)
})
})
describe('when the file does not exist', function () {
let exists
beforeEach(async function () {
GcsFile.exists = sinon.stub().resolves([false])
exists = await GcsPersistor.checkIfObjectExists(bucket, key)
})
it('should get the object header', function () {
expect(Storage.prototype.bucket).to.have.been.calledWith(bucket)
expect(GcsBucket.file).to.have.been.calledWith(key)
expect(GcsFile.exists).to.have.been.called
})
it('should return that the file does not exist', function () {
expect(exists).to.equal(false)
})
})
describe('when there is an error', function () {
let error
beforeEach(async function () {
GcsFile.exists = sinon.stub().rejects(genericError)
try {
await GcsPersistor.checkIfObjectExists(bucket, key)
} catch (err) {
error = err
}
})
it('should generate a ReadError', function () {
expect(error).to.be.an.instanceOf(Errors.ReadError)
})
it('should wrap the error', function () {
expect(error.cause).to.equal(genericError)
})
})
})
})

532
libraries/object-persistor/test/unit/MigrationPersistorTests.js Normal file
View File

@@ -0,0 +1,532 @@
const sinon = require('sinon')
const chai = require('chai')
const { expect } = chai
const modulePath = '../../src/MigrationPersistor.js'
const SandboxedModule = require('sandboxed-module')
const Errors = require('../../src/Errors')
// Not all methods are tested here, but a method with each type of wrapping has
// tests. Specifically, the following wrapping methods are tested here:
// getObjectStream: _wrapFallbackMethod
// sendStream: forward-to-primary
// deleteObject: _wrapMethodOnBothPersistors
// copyObject: copyFileWithFallback
describe('MigrationPersistorTests', function () {
const bucket = 'womBucket'
const fallbackBucket = 'bucKangaroo'
const key = 'monKey'
const destKey = 'donKey'
const genericError = new Error('guru meditation error')
const notFoundError = new Errors.NotFoundError('not found')
const size = 33
const md5 = 'ffffffff'
let Settings,
Logger,
Stream,
StreamPromises,
MigrationPersistor,
fileStream,
newPersistor
beforeEach(function () {
fileStream = {
name: 'fileStream',
on: sinon.stub().withArgs('end').yields(),
pipe: sinon.stub(),
}
newPersistor = function (hasFile) {
return {
sendFile: sinon.stub().resolves(),
sendStream: sinon.stub().resolves(),
getObjectStream: hasFile
? sinon.stub().resolves(fileStream)
: sinon.stub().rejects(notFoundError),
deleteDirectory: sinon.stub().resolves(),
getObjectSize: hasFile
? sinon.stub().resolves(size)
: sinon.stub().rejects(notFoundError),
deleteObject: sinon.stub().resolves(),
copyObject: hasFile
? sinon.stub().resolves()
: sinon.stub().rejects(notFoundError),
checkIfObjectExists: sinon.stub().resolves(hasFile),
directorySize: hasFile
? sinon.stub().resolves(size)
: sinon.stub().rejects(notFoundError),
getObjectMd5Hash: hasFile
? sinon.stub().resolves(md5)
: sinon.stub().rejects(notFoundError),
}
}
Settings = {
buckets: {
[bucket]: fallbackBucket,
},
}
Stream = {
PassThrough: sinon.stub(),
}
StreamPromises = {
pipeline: sinon.stub().resolves(),
}
Logger = {
warn: sinon.stub(),
}
MigrationPersistor = SandboxedModule.require(modulePath, {
requires: {
stream: Stream,
'stream/promises': StreamPromises,
'./Errors': Errors,
'@overleaf/logger': Logger,
},
globals: { console },
})
})
describe('getObjectStream', function () {
const options = { wombat: 'potato' }
describe('when the primary persistor has the file', function () {
let primaryPersistor, fallbackPersistor, migrationPersistor, response
beforeEach(async function () {
primaryPersistor = newPersistor(true)
fallbackPersistor = newPersistor(false)
migrationPersistor = new MigrationPersistor(
primaryPersistor,
fallbackPersistor,
Settings
)
response = await migrationPersistor.getObjectStream(
bucket,
key,
options
)
})
it('should return the file stream', function () {
expect(response).to.equal(fileStream)
})
it('should fetch the file from the primary persistor, with the correct options', function () {
expect(primaryPersistor.getObjectStream).to.have.been.calledWithExactly(
bucket,
key,
options
)
})
it('should not query the fallback persistor', function () {
expect(fallbackPersistor.getObjectStream).not.to.have.been.called
})
})
describe('when the fallback persistor has the file', function () {
let primaryPersistor, fallbackPersistor, migrationPersistor, response
beforeEach(async function () {
primaryPersistor = newPersistor(false)
fallbackPersistor = newPersistor(true)
migrationPersistor = new MigrationPersistor(
primaryPersistor,
fallbackPersistor,
Settings
)
response = await migrationPersistor.getObjectStream(
bucket,
key,
options
)
})
it('should return the file stream', function () {
expect(response).to.be.an.instanceOf(Stream.PassThrough)
})
it('should fetch the file from the primary persistor with the correct options', function () {
expect(primaryPersistor.getObjectStream).to.have.been.calledWithExactly(
bucket,
key,
options
)
})
it('should fetch the file from the fallback persistor with the fallback bucket with the correct options', function () {
expect(
fallbackPersistor.getObjectStream
).to.have.been.calledWithExactly(fallbackBucket, key, options)
})
it('should create one read stream', function () {
expect(fallbackPersistor.getObjectStream).to.have.been.calledOnce
})
it('should not send the file to the primary', function () {
expect(primaryPersistor.sendStream).not.to.have.been.called
})
})
describe('when the file should be copied to the primary', function () {
let primaryPersistor,
fallbackPersistor,
migrationPersistor,
returnedStream
beforeEach(async function () {
primaryPersistor = newPersistor(false)
fallbackPersistor = newPersistor(true)
migrationPersistor = new MigrationPersistor(
primaryPersistor,
fallbackPersistor,
Settings
)
Settings.copyOnMiss = true
returnedStream = await migrationPersistor.getObjectStream(
bucket,
key,
options
)
})
it('should create one read stream', function () {
expect(fallbackPersistor.getObjectStream).to.have.been.calledOnce
})
it('should get the md5 hash from the source', function () {
expect(fallbackPersistor.getObjectMd5Hash).to.have.been.calledWith(
fallbackBucket,
key
)
})
it('should send a stream to the primary', function () {
expect(primaryPersistor.sendStream).to.have.been.calledWithExactly(
bucket,
key,
sinon.match.instanceOf(Stream.PassThrough),
{ sourceMd5: md5 }
)
})
it('should send a stream to the client', function () {
expect(returnedStream).to.be.an.instanceOf(Stream.PassThrough)
})
})
describe('when neither persistor has the file', function () {
it('rejects with a NotFoundError', async function () {
const migrationPersistor = new MigrationPersistor(
newPersistor(false),
newPersistor(false),
Settings
)
await expect(
migrationPersistor.getObjectStream(bucket, key)
).to.eventually.be.rejected.and.be.an.instanceOf(Errors.NotFoundError)
})
})
describe('when the primary persistor throws an unexpected error', function () {
let primaryPersistor, fallbackPersistor, migrationPersistor, error
beforeEach(async function () {
primaryPersistor = newPersistor(false)
fallbackPersistor = newPersistor(true)
primaryPersistor.getObjectStream = sinon.stub().rejects(genericError)
migrationPersistor = new MigrationPersistor(
primaryPersistor,
fallbackPersistor,
Settings
)
try {
await migrationPersistor.getObjectStream(bucket, key, options)
} catch (err) {
error = err
}
})
it('rejects with the error', function () {
expect(error).to.equal(genericError)
})
it('does not call the fallback', function () {
expect(fallbackPersistor.getObjectStream).not.to.have.been.called
})
})
describe('when the fallback persistor throws an unexpected error', function () {
let primaryPersistor, fallbackPersistor, migrationPersistor, error
beforeEach(async function () {
primaryPersistor = newPersistor(false)
fallbackPersistor = newPersistor(false)
fallbackPersistor.getObjectStream = sinon.stub().rejects(genericError)
migrationPersistor = new MigrationPersistor(
primaryPersistor,
fallbackPersistor,
Settings
)
try {
await migrationPersistor.getObjectStream(bucket, key, options)
} catch (err) {
error = err
}
})
it('rejects with the error', function () {
expect(error).to.equal(genericError)
})
it('should have called the fallback', function () {
expect(fallbackPersistor.getObjectStream).to.have.been.calledWith(
fallbackBucket,
key
)
})
})
})
describe('sendStream', function () {
let primaryPersistor, fallbackPersistor, migrationPersistor
beforeEach(function () {
primaryPersistor = newPersistor(false)
fallbackPersistor = newPersistor(false)
migrationPersistor = new MigrationPersistor(
primaryPersistor,
fallbackPersistor,
Settings
)
})
describe('when it works', function () {
beforeEach(async function () {
return migrationPersistor.sendStream(bucket, key, fileStream)
})
it('should send the file to the primary persistor', function () {
expect(primaryPersistor.sendStream).to.have.been.calledWithExactly(
bucket,
key,
fileStream
)
})
it('should not send the file to the fallback persistor', function () {
expect(fallbackPersistor.sendStream).not.to.have.been.called
})
})
describe('when the primary persistor throws an error', function () {
it('returns the error', async function () {
primaryPersistor.sendStream.rejects(notFoundError)
await expect(
migrationPersistor.sendStream(bucket, key, fileStream)
).to.eventually.be.rejected.and.be.an.instanceOf(Errors.NotFoundError)
})
})
})
describe('deleteObject', function () {
let primaryPersistor, fallbackPersistor, migrationPersistor
beforeEach(function () {
primaryPersistor = newPersistor(false)
fallbackPersistor = newPersistor(false)
migrationPersistor = new MigrationPersistor(
primaryPersistor,
fallbackPersistor,
Settings
)
})
describe('when it works', function () {
beforeEach(async function () {
return migrationPersistor.deleteObject(bucket, key)
})
it('should delete the file from the primary', function () {
expect(primaryPersistor.deleteObject).to.have.been.calledWithExactly(
bucket,
key
)
})
it('should delete the file from the fallback', function () {
expect(fallbackPersistor.deleteObject).to.have.been.calledWithExactly(
fallbackBucket,
key
)
})
})
describe('when the primary persistor throws an error', function () {
let error
beforeEach(async function () {
primaryPersistor.deleteObject.rejects(genericError)
try {
await migrationPersistor.deleteObject(bucket, key)
} catch (err) {
error = err
}
})
it('should return the error', function () {
expect(error).to.equal(genericError)
})
it('should delete the file from the primary', function () {
expect(primaryPersistor.deleteObject).to.have.been.calledWithExactly(
bucket,
key
)
})
it('should delete the file from the fallback', function () {
expect(fallbackPersistor.deleteObject).to.have.been.calledWithExactly(
fallbackBucket,
key
)
})
})
describe('when the fallback persistor throws an error', function () {
let error
beforeEach(async function () {
fallbackPersistor.deleteObject.rejects(genericError)
try {
await migrationPersistor.deleteObject(bucket, key)
} catch (err) {
error = err
}
})
it('should return the error', function () {
expect(error).to.equal(genericError)
})
it('should delete the file from the primary', function () {
expect(primaryPersistor.deleteObject).to.have.been.calledWithExactly(
bucket,
key
)
})
it('should delete the file from the fallback', function () {
expect(fallbackPersistor.deleteObject).to.have.been.calledWithExactly(
fallbackBucket,
key
)
})
})
})
describe('copyObject', function () {
describe('when the file exists on the primary', function () {
let primaryPersistor, fallbackPersistor, migrationPersistor
beforeEach(async function () {
primaryPersistor = newPersistor(true)
fallbackPersistor = newPersistor(false)
migrationPersistor = new MigrationPersistor(
primaryPersistor,
fallbackPersistor,
Settings
)
return migrationPersistor.copyObject(bucket, key, destKey)
})
it('should call copyObject to copy the file', function () {
expect(primaryPersistor.copyObject).to.have.been.calledWithExactly(
bucket,
key,
destKey
)
})
it('should not try to read from the fallback', function () {
expect(fallbackPersistor.getObjectStream).not.to.have.been.called
})
})
describe('when the file does not exist on the primary', function () {
let primaryPersistor, fallbackPersistor, migrationPersistor
beforeEach(async function () {
primaryPersistor = newPersistor(false)
fallbackPersistor = newPersistor(true)
migrationPersistor = new MigrationPersistor(
primaryPersistor,
fallbackPersistor,
Settings
)
return migrationPersistor.copyObject(bucket, key, destKey)
})
it('should call copyObject to copy the file', function () {
expect(primaryPersistor.copyObject).to.have.been.calledWithExactly(
bucket,
key,
destKey
)
})
it('should fetch the file from the fallback', function () {
expect(
fallbackPersistor.getObjectStream
).not.to.have.been.calledWithExactly(fallbackBucket, key)
})
it('should get the md5 hash from the source', function () {
expect(fallbackPersistor.getObjectMd5Hash).to.have.been.calledWith(
fallbackBucket,
key
)
})
it('should send the file to the primary', function () {
expect(primaryPersistor.sendStream).to.have.been.calledWithExactly(
bucket,
destKey,
sinon.match.instanceOf(Stream.PassThrough),
{ sourceMd5: md5 }
)
})
})
describe('when the file does not exist on the fallback', function () {
let primaryPersistor, fallbackPersistor, migrationPersistor, error
beforeEach(async function () {
primaryPersistor = newPersistor(false)
fallbackPersistor = newPersistor(false)
migrationPersistor = new MigrationPersistor(
primaryPersistor,
fallbackPersistor,
Settings
)
try {
await migrationPersistor.copyObject(bucket, key, destKey)
} catch (err) {
error = err
}
})
it('should call copyObject to copy the file', function () {
expect(primaryPersistor.copyObject).to.have.been.calledWithExactly(
bucket,
key,
destKey
)
})
it('should fetch the file from the fallback', function () {
expect(
fallbackPersistor.getObjectStream
).not.to.have.been.calledWithExactly(fallbackBucket, key)
})
it('should return a not-found error', function () {
expect(error).to.be.an.instanceOf(Errors.NotFoundError)
})
})
})
})

102
libraries/object-persistor/test/unit/PersistorFactoryTests.js Normal file
View File

@@ -0,0 +1,102 @@
const chai = require('chai')
const { expect } = chai
const SandboxedModule = require('sandboxed-module')
const StreamPromises = require('node:stream/promises')
const MODULE_PATH = '../../src/PersistorFactory.js'
describe('PersistorManager', function () {
let PersistorFactory, FSPersistor, S3Persistor, Settings, GcsPersistor
beforeEach(function () {
FSPersistor = class {
constructor(settings) {
this.settings = settings
}
wrappedMethod() {
return 'FSPersistor'
}
}
S3Persistor = class {
wrappedMethod() {
return 'S3Persistor'
}
}
GcsPersistor = class {
wrappedMethod() {
return 'GcsPersistor'
}
}
Settings = {}
const requires = {
'./GcsPersistor': GcsPersistor,
'./S3Persistor': { S3Persistor },
'./FSPersistor': FSPersistor,
'@overleaf/logger': {
info() {},
err() {},
},
'stream/promises': StreamPromises,
}
PersistorFactory = SandboxedModule.require(MODULE_PATH, { requires })
})
it('should implement the S3 wrapped method when S3 is configured', function () {
Settings.backend = 's3'
expect(PersistorFactory(Settings)).to.respondTo('wrappedMethod')
expect(PersistorFactory(Settings).wrappedMethod()).to.equal('S3Persistor')
})
it("should implement the S3 wrapped method when 'aws-sdk' is configured", function () {
Settings.backend = 'aws-sdk'
expect(PersistorFactory(Settings)).to.respondTo('wrappedMethod')
expect(PersistorFactory(Settings).wrappedMethod()).to.equal('S3Persistor')
})
it('should implement the FS wrapped method when FS is configured', function () {
Settings.backend = 'fs'
expect(PersistorFactory(Settings)).to.respondTo('wrappedMethod')
expect(PersistorFactory(Settings).wrappedMethod()).to.equal('FSPersistor')
})
it('should forward useSubdirectories=true to FSPersistor', function () {
Settings.backend = 'fs'
Settings.useSubdirectories = true
expect(PersistorFactory(Settings).settings.useSubdirectories).to.be.true
})
it('should forward useSubdirectories=false to FSPersistor', function () {
Settings.backend = 'fs'
Settings.useSubdirectories = false
expect(PersistorFactory(Settings).settings.useSubdirectories).to.be.false
})
it('should throw an error when the backend is not configured', function () {
try {
PersistorFactory(Settings)
} catch (err) {
expect(err.message).to.equal('no backend specified - config incomplete')
return
}
expect('should have caught an error').not.to.exist
})
it('should throw an error when the backend is unknown', function () {
Settings.backend = 'magic'
try {
PersistorFactory(Settings)
} catch (err) {
expect(err.message).to.equal('unknown backend')
expect(err.info.backend).to.equal('magic')
return
}
expect('should have caught an error').not.to.exist
})
})

1048
libraries/object-persistor/test/unit/S3PersistorTests.js Normal file
View File

File diff suppressed because it is too large Load Diff

7
libraries/object-persistor/tsconfig.json Normal file
View File

@@ -0,0 +1,7 @@
{
"extends": "../../tsconfig.backend.json",
"include": [
"**/*.js",
"**/*.cjs"
]
}