71 Commits

Author SHA1 Message Date
Sunshine
cbbb297473 Merge pull request #251 from snshn/bump-version-again
Bump version number to 2.4.1
2021-03-09 02:17:17 -10:00
Sunshine
98ddb821a5 bump version number 2021-03-09 02:07:07 -10:00
Sunshine
be097b1d4e Merge pull request #250 from snshn/alternate-stylesheets
Embed alternate stylesheets
2021-03-09 01:58:08 -10:00
Sunshine
325688acf5 add test for alternate stylesheets 2021-03-09 01:48:41 -10:00
Sunshine
11207d49d2 embed alternate stylesheets 2021-03-09 01:46:15 -10:00
Sunshine
96da64e193 Merge pull request #247 from snshn/cc0
Change project license to CC0 1.0 Universal (CC0 1.0)
2021-03-01 13:28:49 -10:00
Sunshine
8a62a51210 Merge pull request #248 from snshn/update-container-instructions
Running in container instructions update
2021-02-28 23:24:10 -10:00
Sunshine
a6ac1df93d running in container instructions update 2021-02-28 21:46:38 -10:00
Sunshine
49e81149df switch license to CC0-1.0 2021-02-28 19:54:46 -10:00
Sunshine
a3516b2ae9 Merge pull request #245 from snshn/change-meta-charset-to-utf-8
Forcefully set document's charset to UTF-8
2021-02-23 23:48:49 -10:00
Sunshine
385301bf16 clean up unused code 2021-02-23 23:39:51 -10:00
Sunshine
4921a70dda Merge branch 'master' into change-meta-charset-to-utf-8 2021-02-23 23:38:03 -10:00
Sunshine
e0273c664a forcefully set document's charset to UTF-8 2021-02-23 23:35:35 -10:00
Sunshine
6d629bfd4a Merge pull request #244 from snshn/process-noscript
Process contents of NOSCRIPT tags
2021-02-22 20:13:26 -10:00
Sunshine
ae9d78a891 process contents of NOSCRIPT tags 2021-02-22 19:42:39 -10:00
Sunshine
0f55fb3c49 Merge pull request #243 from snshn/fix-embedding-picture-srcset
Fix embedding of srcset assets for PICTURE nodes
2021-02-22 16:27:22 -10:00
Sunshine
e41fd6a1c6 fix embedding of srcset for PICTURE nodes 2021-02-22 16:21:12 -10:00
Sunshine
eaf662bb3b Update README.md 2021-02-15 15:38:06 -10:00
Sunshine
fa71f6a42c Merge pull request #240 from snshn/color
Add color to asset download log
2021-01-30 10:48:35 -10:00
Sunshine
9a27c6c5ee add color to asset download log 2021-01-29 20:24:35 -10:00
Sunshine
4ad07c0519 Merge pull request #239 from snshn/update-crates
Update dependencies
2021-01-29 17:27:43 -10:00
Sunshine
e78405f2ae update dependencies 2021-01-29 17:19:38 -10:00
Sunshine
e81462be41 Merge pull request #237 from snshn/choco
Add Chocolatey spec file
2020-12-31 15:32:27 -10:00
Sunshine
b972d717ce add chocolatey spec 2020-12-31 15:30:41 -10:00
Sunshine
edb679d2b3 Merge pull request #236 from snshn/pipe-in-target-test
Add test for stdin pipe
2020-12-31 14:44:57 -10:00
Sunshine
2e1462a953 add test for stdin pipe 2020-12-31 14:38:31 -10:00
Sunshine
57883b84b2 Merge pull request #235 from snshn/allow-empty-user-agent-string
Make it possible to specify an empty user-agent string
2020-12-31 13:02:35 -10:00
Sunshine
4fa2eda983 make it possible to specify an empty user-agent string 2020-12-31 12:57:22 -10:00
Sunshine
028187a31e Merge pull request #234 from snshn/update-dependencies
Update crates
2020-12-28 12:11:25 -10:00
Sunshine
c469c30cbd update crates 2020-12-28 12:04:27 -10:00
Sunshine
6de36243f9 Fix armhf build in cd.yml 2020-12-27 05:52:47 -10:00
Sunshine
4f162d0cc0 Update README.md 2020-12-25 22:59:24 -10:00
Sunshine
95040173fc Merge pull request #233 from snshn/cargo-fix-license-identifier
Fix license identifier in Cargo.toml
2020-12-25 22:42:31 -10:00
Sunshine
b10d41f82e fix license identifier in Cargo.toml 2020-12-25 22:41:31 -10:00
Sunshine
4c2c55d166 Merge pull request #232 from snshn/fix-cargo-toml
Reduce amount of keywords to 5 (max)
2020-12-25 22:34:08 -10:00
Sunshine
2dd1c465e4 reduce amount of keywords to 5 (max) 2020-12-25 22:28:19 -10:00
Sunshine
a5afda9c80 Merge pull request #229 from snshn/cargo-install
Update Cargo.toml for publishing on crates.io
2020-12-25 22:15:13 -10:00
Sunshine
ab6fed6d1f Merge pull request #231 from snshn/fix-srcset
Fix srcset parsing
2020-12-25 22:07:45 -10:00
Sunshine
f8dcb335e7 bump version, make possible to install via cargo 2020-12-25 22:07:19 -10:00
Sunshine
913051870a Merge pull request #230 from snshn/stdin
Make possible to use stdin as input method
2020-12-25 21:58:14 -10:00
Sunshine
614a518475 fix srcset parsing 2020-12-25 21:56:40 -10:00
Sunshine
870a4b150e make possible to use stdin as input method 2020-12-25 21:23:29 -10:00
Sunshine
0533b287b7 Merge pull request #228 from snshn/audio-video-support
Add support for embedding video and audio files
2020-12-25 16:55:42 -10:00
Sunshine
4ba4285b6b add support for embedding video and audio files 2020-12-25 16:49:43 -10:00
Sunshine
2b9caf9840 Merge pull request #227 from snshn/fix-trailing-comma-for-srcset-parsing
Fix crash associated with trailing/repeating commas within srcset
2020-12-25 14:33:20 -10:00
Sunshine
8adf059980 fix crash associated with trailing/repeating commas within srcset 2020-12-25 14:24:52 -10:00
Sunshine
8ad252868e Merge pull request #226 from snshn/base-tag-option
Add base URL option
2020-12-25 13:02:05 -10:00
Sunshine
e145df372f Merge branch 'master' into base-tag-option 2020-12-25 12:10:54 -10:00
Sunshine
816b6175ac rewrite ADR #8 (Base Tag) 2020-12-25 12:06:56 -10:00
Sunshine
d89b4d5f5b refactor code that processes the DOM 2020-12-25 11:09:47 -10:00
Sunshine
15d98a7269 don't modify base url by default, add option for setting it 2020-12-24 18:38:44 -10:00
Sunshine
36e82cb511 Update README.md 2020-12-13 08:42:41 -10:00
Sunshine
1b1befd7b0 Merge pull request #222 from snshn/readme-no-metadata-info
Add description of -M option to README.md
2020-12-09 21:29:33 -05:00
Sunshine
a2f59b4418 Update README.md 2020-12-09 16:23:17 -10:00
Sunshine
124a62920f Merge pull request #221 from snshn/related-project-hako
Add Hako
2020-12-09 07:54:52 -05:00
Sunshine
f557504bed Update README.md
Add Hako to the list of related projects
2020-12-08 17:02:09 -10:00
Sunshine
5ac520b4da Merge pull request #219 from snshn/ignore-network-errors-option
Account for network errors
2020-11-22 17:54:30 -10:00
Sunshine
7a97291498 add ADR 7 (Network errors) 2020-11-22 17:20:37 -10:00
Sunshine
38a6f963ad account for network errors, add option to ignore them 2020-11-22 16:49:26 -10:00
Sunshine
052f8f49ec Merge pull request #218 from snshn/update-crates
Update crates
2020-11-20 00:36:33 -10:00
Sunshine
08de486382 use newer dependencies 2020-11-20 00:30:05 -10:00
Sunshine
c0e0a69773 Merge pull request #214 from zfhrp6/remove_use_unused_opts
remove unused import opts::Options;
2020-11-04 01:04:38 -08:00
Sunshine
1636540693 Merge pull request #216 from zfhrp6/suppress_deprecation_of_dependency
update clap 2.33.1 -> 2.33.3
2020-11-02 19:03:43 -08:00
zfhrp
3e80cb02ce update clap 2.33.1 -> 2.33.3 2020-11-02 00:11:41 +09:00
zfhrp
a296531b3f remove unused import opts::Options; 2020-11-01 23:04:08 +09:00
Sunshine
8462b6bc31 Merge pull request #207 from snshn/bump-version
bump version (2.3.0 -> 2.3.1)
2020-08-01 21:00:26 -04:00
Sunshine
92f38556b6 bump version (2.3.0 -> 2.3.1) 2020-08-01 20:24:38 -04:00
Sunshine
c0bdeab2e3 Merge pull request #206 from snshn/update-crates
Update crates
2020-08-01 19:43:00 -04:00
Sunshine
5a502eab4b update crate versions 2020-08-01 19:20:20 -04:00
Sunshine
19f08265a2 Merge pull request #205 from snshn/base-tag
Implement support for BASE tag
2020-08-01 02:47:33 -04:00
Sunshine
1d6392cb28 implement support for BASE tag 2020-08-01 02:35:07 -04:00
47 changed files with 3304 additions and 2118 deletions

View File

@@ -39,11 +39,11 @@ jobs:
sudo dpkg -x libssl1.1*.deb /cross-build-arm
sudo dpkg -x libssl-dev*.deb /cross-build-arm
rustup target add arm-unknown-linux-gnueabihf
echo "::set-env name=C_INCLUDE_PATH::/cross-build-arm/usr/include"
echo "::set-env name=OPENSSL_INCLUDE_DIR::/cross-build-arm/usr/include/arm-linux-gnueabihf"
echo "::set-env name=OPENSSL_LIB_DIR::/cross-build-arm/usr/lib/arm-linux-gnueabihf"
echo "::set-env name=PKG_CONFIG_ALLOW_CROSS::1"
echo "::set-env name=RUSTFLAGS::-C linker=arm-linux-gnueabihf-gcc -L/usr/arm-linux-gnueabihf/lib -L/cross-build-arm/usr/lib/arm-linux-gnueabihf -L/cross-build-arm/lib/arm-linux-gnueabihf"
echo "C_INCLUDE_PATH=/cross-build-arm/usr/include" >> $GITHUB_ENV
echo "OPENSSL_INCLUDE_DIR=/cross-build-arm/usr/include/arm-linux-gnueabihf" >> $GITHUB_ENV
echo "OPENSSL_LIB_DIR=/cross-build-arm/usr/lib/arm-linux-gnueabihf" >> $GITHUB_ENV
echo "PKG_CONFIG_ALLOW_CROSS=1" >> $GITHUB_ENV
echo "RUSTFLAGS=-C linker=arm-linux-gnueabihf-gcc -L/usr/arm-linux-gnueabihf/lib -L/cross-build-arm/usr/lib/arm-linux-gnueabihf -L/cross-build-arm/lib/arm-linux-gnueabihf" >> $GITHUB_ENV
- name: Build the executable
run: cargo build --release --target=arm-unknown-linux-gnueabihf
- name: Attach artifact to the release

1374
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -1,7 +1,6 @@
[package]
name = "monolith"
version = "2.3.0"
edition = "2018"
version = "2.4.1"
authors = [
"Sunshine <sunshine@uberspace.net>",
"Mahdi Robatipoor <mahdi.robatipoor@gmail.com>",
@@ -9,22 +8,35 @@ authors = [
"Emi Simpson <emi@alchemi.dev>",
"rhysd <lin90162@yahoo.co.jp>",
]
edition = "2018"
description = "CLI tool for saving web pages as a single HTML file"
homepage = "https://github.com/Y2Z/monolith"
repository = "https://github.com/Y2Z/monolith"
readme = "README.md"
keywords = ["web", "http", "html", "download", "command-line"]
categories = ["command-line-utilities", "web-programming"]
include = [
"src/*.rs",
"Cargo.toml",
]
license = "CC0-1.0"
[dependencies]
base64 = "0.12.2"
chrono = "0.4.11" # Used to render comments indicating the time the page was saved
clap = "2.33.1"
cssparser = "0.27.2"
atty = "0.2" # Used for highlighting network errors
base64 = "0.13.0"
chrono = "0.4.19" # Used for formatting creation timestamp
clap = "2.33.3"
cssparser = "0.28.1"
html5ever = "0.24.1"
sha2 = "0.9.0" # Used in calculating checksums during integrity checks
url = "2.1.1"
regex = "1.4.3" # Used for parsing srcset
sha2 = "0.9.2" # Used for calculating checksums during integrity checks
url = "2.2.0"
[dependencies.reqwest]
version = "0.10.6"
version = "0.11.0"
default-features = false
features = ["default-tls", "blocking", "gzip"]
[dev-dependencies]
assert_cmd = "1.0.1"
tempfile = "3.1.0"
assert_cmd = "1.0.2"
tempfile = "3.2.0"

View File

@@ -2,13 +2,13 @@ FROM rust
WORKDIR /usr/local/src/
RUN curl -s https://api.github.com/repos/y2z/monolith/releases/latest \
| grep "tarball_url.*\"," \
| cut -d '"' -f 4 \
| wget -qi - -O monolith.tar.gz
| grep "tarball_url.*\"," \
| cut -d '"' -f 4 \
| wget -qi - -O monolith.tar.gz
RUN tar xfz monolith.tar.gz \
&& mv Y2Z-monolith-* monolith \
&& rm monolith.tar.gz
&& mv Y2Z-monolith-* monolith \
&& rm monolith.tar.gz
WORKDIR /usr/local/src/monolith
RUN ls -a

137
LICENSE
View File

@@ -1,24 +1,121 @@
This is free and unencumbered software released into the public domain.
Creative Commons Legal Code
Anyone is free to copy, modify, publish, use, compile, sell, or
distribute this software, either in source code form or as a compiled
binary, for any purpose, commercial or non-commercial, and by any
means.
CC0 1.0 Universal
In jurisdictions that recognize copyright laws, the author or authors
of this software dedicate any and all copyright interest in the
software to the public domain. We make this dedication for the benefit
of the public at large and to the detriment of our heirs and
successors. We intend this dedication to be an overt act of
relinquishment in perpetuity of all present and future rights to this
software under copyright law.
CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE
LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN
ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS
INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES
REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS
PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM
THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED
HEREUNDER.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
OTHER DEALINGS IN THE SOFTWARE.
Statement of Purpose
For more information, please refer to <http://unlicense.org>
The laws of most jurisdictions throughout the world automatically confer
exclusive Copyright and Related Rights (defined below) upon the creator
and subsequent owner(s) (each and all, an "owner") of an original work of
authorship and/or a database (each, a "Work").
Certain owners wish to permanently relinquish those rights to a Work for
the purpose of contributing to a commons of creative, cultural and
scientific works ("Commons") that the public can reliably and without fear
of later claims of infringement build upon, modify, incorporate in other
works, reuse and redistribute as freely as possible in any form whatsoever
and for any purposes, including without limitation commercial purposes.
These owners may contribute to the Commons to promote the ideal of a free
culture and the further production of creative, cultural and scientific
works, or to gain reputation or greater distribution for their Work in
part through the use and efforts of others.
For these and/or other purposes and motivations, and without any
expectation of additional consideration or compensation, the person
associating CC0 with a Work (the "Affirmer"), to the extent that he or she
is an owner of Copyright and Related Rights in the Work, voluntarily
elects to apply CC0 to the Work and publicly distribute the Work under its
terms, with knowledge of his or her Copyright and Related Rights in the
Work and the meaning and intended legal effect of CC0 on those rights.
1. Copyright and Related Rights. A Work made available under CC0 may be
protected by copyright and related or neighboring rights ("Copyright and
Related Rights"). Copyright and Related Rights include, but are not
limited to, the following:
i. the right to reproduce, adapt, distribute, perform, display,
communicate, and translate a Work;
ii. moral rights retained by the original author(s) and/or performer(s);
iii. publicity and privacy rights pertaining to a person's image or
likeness depicted in a Work;
iv. rights protecting against unfair competition in regards to a Work,
subject to the limitations in paragraph 4(a), below;
v. rights protecting the extraction, dissemination, use and reuse of data
in a Work;
vi. database rights (such as those arising under Directive 96/9/EC of the
European Parliament and of the Council of 11 March 1996 on the legal
protection of databases, and under any national implementation
thereof, including any amended or successor version of such
directive); and
vii. other similar, equivalent or corresponding rights throughout the
world based on applicable law or treaty, and any national
implementations thereof.
2. Waiver. To the greatest extent permitted by, but not in contravention
of, applicable law, Affirmer hereby overtly, fully, permanently,
irrevocably and unconditionally waives, abandons, and surrenders all of
Affirmer's Copyright and Related Rights and associated claims and causes
of action, whether now known or unknown (including existing as well as
future claims and causes of action), in the Work (i) in all territories
worldwide, (ii) for the maximum duration provided by applicable law or
treaty (including future time extensions), (iii) in any current or future
medium and for any number of copies, and (iv) for any purpose whatsoever,
including without limitation commercial, advertising or promotional
purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each
member of the public at large and to the detriment of Affirmer's heirs and
successors, fully intending that such Waiver shall not be subject to
revocation, rescission, cancellation, termination, or any other legal or
equitable action to disrupt the quiet enjoyment of the Work by the public
as contemplated by Affirmer's express Statement of Purpose.
3. Public License Fallback. Should any part of the Waiver for any reason
be judged legally invalid or ineffective under applicable law, then the
Waiver shall be preserved to the maximum extent permitted taking into
account Affirmer's express Statement of Purpose. In addition, to the
extent the Waiver is so judged Affirmer hereby grants to each affected
person a royalty-free, non transferable, non sublicensable, non exclusive,
irrevocable and unconditional license to exercise Affirmer's Copyright and
Related Rights in the Work (i) in all territories worldwide, (ii) for the
maximum duration provided by applicable law or treaty (including future
time extensions), (iii) in any current or future medium and for any number
of copies, and (iv) for any purpose whatsoever, including without
limitation commercial, advertising or promotional purposes (the
"License"). The License shall be deemed effective as of the date CC0 was
applied by Affirmer to the Work. Should any part of the License for any
reason be judged legally invalid or ineffective under applicable law, such
partial invalidity or ineffectiveness shall not invalidate the remainder
of the License, and in such case Affirmer hereby affirms that he or she
will not (i) exercise any of his or her remaining Copyright and Related
Rights in the Work or (ii) assert any associated claims and causes of
action with respect to the Work, in either case contrary to Affirmer's
express Statement of Purpose.
4. Limitations and Disclaimers.
a. No trademark or patent rights held by Affirmer are waived, abandoned,
surrendered, licensed or otherwise affected by this document.
b. Affirmer offers the Work as-is and makes no representations or
warranties of any kind concerning the Work, express, implied,
statutory or otherwise, including without limitation warranties of
title, merchantability, fitness for a particular purpose, non
infringement, or the absence of latent or other defects, accuracy, or
the present or absence of errors, whether or not discoverable, all to
the greatest extent permissible under applicable law.
c. Affirmer disclaims responsibility for clearing rights of other persons
that may apply to the Work or any use thereof, including without
limitation any person's Copyright and Related Rights in the Work.
Further, Affirmer disclaims responsibility for obtaining any necessary
consents, permissions or other rights required for any use of the
Work.
d. Affirmer understands and acknowledges that Creative Commons is not a
party to this document and has no duty or obligation with respect to
this CC0 or use of the Work.

View File

@@ -10,7 +10,7 @@ build:
test: build
@cargo test --locked
@cargo fmt --all -- --check
.PHONY: test_code_formatting
.PHONY: test
lint:
@cargo fmt --all --

View File

@@ -22,6 +22,9 @@ If compared to saving websites with `wget -mpk`, this tool embeds all assets as
## Installation
### Using Cargo
$ cargo install monolith
#### Via Homebrew (on macOS and GNU/Linux)
$ brew install monolith
@@ -44,31 +47,41 @@ Dependency: `libssl-dev`
$ make install
#### Using Containers
The guide can be found [here](docs/containers.md)
$ docker build -t Y2Z/monolith .
$ sudo install -b utils/run-in-container.sh /usr/local/bin/monolith
---------------------------------------------------
## Usage
$ monolith https://lyrics.github.io/db/P/Portishead/Dummy/Roads/ -o portishead-roads-lyrics.html
or
$ cat index.html | monolith -aIiFfcMv - > index-processed.html
---------------------------------------------------
## Options
- `-c`: Ignore styles
- `-f`: Exclude frames
- `-F`: Omit web fonts
- `-a`: Exclude audio sources
- `-b`: Use custom `base URL`
- `-c`: Exclude CSS
- `-e`: Ignore network errors
- `-f`: Omit frames
- `-F`: Exclude web fonts
- `-i`: Remove images
- `-I`: Isolate the document
- `-j`: Exclude JavaScript
- `-k`: Accept invalid X.509 (TLS) certificates
- `-o`: Write output to file
- `-M`: Don't add timestamp and URL information
- `-o`: Write output to `file`
- `-s`: Be quiet
- `-t`: Adjust network request timeout
- `-u`: Provide custom User-Agent
- `-t`: Adjust `network request timeout`
- `-u`: Provide `custom User-Agent`
- `-v`: Exclude videos
---------------------------------------------------
## HTTPS and HTTP proxies
## Proxies
Please set `https_proxy`, `http_proxy`, and `no_proxy` environment variables.
---------------------------------------------------
@@ -82,11 +95,18 @@ Please open an issue if something is wrong, that helps make this project better.
- `Monolith Chrome Extension`: https://github.com/rhysd/monolith-of-web
- `Pagesaver`: https://github.com/distributed-mind/pagesaver
- `Personal WayBack Machine`: https://github.com/popey/pwbm
- `Hako`: https://github.com/dmpop/hako
---------------------------------------------------
## License
The Unlicense
<a href="http://creativecommons.org/publicdomain/zero/1.0/">
<img src="http://i.creativecommons.org/p/zero/1.0/88x31.png" alt="CC0-1.0" />
</a>
<br />
To the extent possible under law, the author(s) have dedicated all copyright related and neighboring rights to this software to the public domain worldwide.
This software is distributed without any warranty.
---------------------------------------------------

View File

@@ -1,4 +1,4 @@
# 2. Network request timeout
# 3. Network request timeout
Date: 2020-02-15

View File

@@ -1,4 +1,4 @@
# 4. Asset Minimization
# 5. Asset Minimization
Date: 2020-03-14

View File

@@ -1,4 +1,4 @@
# 4. Reload and location `meta` tags
# 6. Reload and location `meta` tags
Date: 2020-06-25

View File

@@ -0,0 +1,19 @@
# 7. Network errors
Date: 2020-11-22
## Status
Accepted
## Context
Servers may return information with HTTP response codes other than `200`, however those responses may still contain useful data.
## Decision
Fail by default, notifying of the network error. Add option to continue retrieving assets by treating all response codes as `200`.
## Consequences
Monolith will fail to obtain resources with status other than `200`, unless told to ignore network errors.

View File

@@ -0,0 +1,40 @@
# 8. Base Tag
Date: 2020-12-25
## Status
Accepted
## Context
HTML documents may contain `base` tag, which influences resolution of anchor links and relative URLs as well as dynamically loaded resources.
Sometimes, in order to make certain saved documents function closer to how they operate while being served from a remote server, the `base` tag specifying the source page's URL may need to be added to the document.
There can be only one such tag. If multiple `base` tags are present, only the first encountered tag ends up being used.
## Decision
Adding the `base` tag should be optional — saved documents should not contain the `base` tag unless it was specified by the user, or the document originally had the `base` tag in it.
Existing `href` attribute's value of the original `base` tag should be used for resolving the document's relative links instead of document's own URL (precisely the way browsers do it).
## Consequences
#### If the base tag does not exist in the source document
- If the base tag does not exist in the source document
- With base URL option provided
- use the specified base URL value to retrieve assets, keep original base URL value in the document
- Without base URL option provided
- download document as usual, do not add base tag
- If the base tag already exists in the source document
- With base URL option provided
- we overwrite the original base URL before retrieving assets, keep new base URL value in the document
- Without base URL option provided:
- use the base URL from the original document to retrieve assets, keep original base URL value in the document
The program will obtain ability to retrieve remote assets for non-remote sources (such as data URLs and local files).
The program will obatin ability to get rid of existing base tag values (by provind an empty one).

25
monolith.nuspec Normal file
View File

@@ -0,0 +1,25 @@
<?xml version="1.0" encoding="utf-8"?>
<package xmlns="http://schemas.microsoft.com/packaging/2015/06/nuspec.xsd">
<metadata>
<id>monolith</id>
<version>2.4.0</version>
<title>Monolith</title>
<authors>Sunshine, Mahdi Robatipoor, Emmanuel Delaborde, Emi Simpson, rhysd</authors>
<projectUrl>https://github.com/Y2Z/monolith</projectUrl>
<iconUrl>https://raw.githubusercontent.com/Y2Z/monolith/master/assets/icon/icon.png</iconUrl>
<licenseUrl>https://raw.githubusercontent.com/Y2Z/monolith/master/LICENSE</licenseUrl>
<requireLicenseAcceptance>false</requireLicenseAcceptance>
<description>CLI tool for saving complete web pages as a single HTML file
A data hoarders dream come true: bundle any web page into a single HTML file. You can finally replace that gazillion of open tabs with a gazillion of .html files stored somewhere on your precious little drive.
Unlike the conventional “Save page as”, monolith not only saves the target document, it embeds CSS, image, and JavaScript assets all at once, producing a single HTML5 document that is a joy to store and share.
If compared to saving websites using wget, this tool embeds all assets as data URLs and therefore lets browsers render the saved page exactly the way it was on the Internet, even when no network connection is available.
</description>
<copyright>Public Domain</copyright>
<language>en-US</language>
<tags>scraping archiving</tags>
<docsUrl>https://github.com/Y2Z/monolith/blob/master/README.md</docsUrl>
</metadata>
</package>

View File

@@ -26,7 +26,7 @@ const CSS_PROPS_WITH_IMAGE_URLS: &[&str] = &[
"suffix",
"symbols",
];
const CSS_SPECIAL_CHARS: &str = "~!@$%^&*()+=,./'\";:?><[]{}|`#";
const CSS_SPECIAL_CHARS: &'static str = "~!@$%^&*()+=,./'\";:?><[]{}|`#";
pub fn is_image_url_prop(prop_name: &str) -> bool {
CSS_PROPS_WITH_IMAGE_URLS
@@ -176,7 +176,7 @@ pub fn process_css<'a>(
client,
&parent_url,
&import_full_url,
options.silent,
options,
depth + 1,
) {
Ok((import_contents, import_final_url, _import_media_type)) => {
@@ -227,7 +227,7 @@ pub fn process_css<'a>(
client,
&parent_url,
&resolved_url,
options.silent,
options,
depth + 1,
) {
Ok((data, final_url, media_type)) => {
@@ -315,14 +315,8 @@ pub fn process_css<'a>(
if is_import {
let full_url = resolve_url(&parent_url, value).unwrap_or_default();
let url_fragment = get_url_fragment(full_url.clone());
match retrieve_asset(
cache,
client,
&parent_url,
&full_url,
options.silent,
depth + 1,
) {
match retrieve_asset(cache, client, &parent_url, &full_url, options, depth + 1)
{
Ok((css, final_url, _media_type)) => {
let data_url = data_to_data_url(
"text/css",
@@ -361,7 +355,7 @@ pub fn process_css<'a>(
client,
&parent_url,
&full_url,
options.silent,
options,
depth + 1,
) {
Ok((data, final_url, media_type)) => {

File diff suppressed because it is too large Load Diff

View File

@@ -1,4 +1,4 @@
const JS_DOM_EVENT_ATTRS: &[&str] = &[
const JS_DOM_EVENT_ATTRS: &'static [&str] = &[
// From WHATWG HTML spec 8.1.5.2 "Event handlers on elements, Document objects, and Window objects":
// https://html.spec.whatwg.org/#event-handlers-on-elements,-document-objects,-and-window-objects
// https://html.spec.whatwg.org/#attributes-3 (table "List of event handler content attributes")

View File

@@ -3,17 +3,18 @@ use reqwest::header::{HeaderMap, HeaderValue, USER_AGENT};
use std::collections::HashMap;
use std::env;
use std::fs;
use std::io::{self, Error, Write};
use std::io::{self, prelude::*, Error, Write};
use std::path::Path;
use std::process;
use std::time::Duration;
use monolith::html::{
add_favicon, has_favicon, html_to_dom, metadata_tag, stringify_document, walk_and_embed_assets,
add_favicon, create_metadata_tag, get_base_url, has_favicon, html_to_dom, set_base_url,
stringify_document, walk_and_embed_assets,
};
use monolith::opts::Options;
use monolith::url::{
data_to_data_url, data_url_to_data, is_data_url, is_file_url, is_http_url, resolve_url,
data_to_data_url, is_data_url, is_file_url, is_http_url, parse_data_url, resolve_url,
};
use monolith::utils::retrieve_asset;
@@ -47,12 +48,22 @@ impl Output {
}
}
pub fn read_stdin() -> String {
let mut buffer = String::new();
for line in io::stdin().lock().lines() {
buffer += line.unwrap_or_default().as_str();
buffer += "\n";
}
buffer
}
fn main() {
let options = Options::from_args();
let original_target: &str = &options.target;
let target_url: &str;
let base_url;
let mut base_url: String;
let mut dom;
let mut use_stdin: bool = false;
// Pre-process the input
let cwd_normalized: String =
@@ -63,15 +74,24 @@ fn main() {
// Determine exact target URL
if target.clone().len() == 0 {
eprintln!("No target specified");
if !options.silent {
eprintln!("No target specified");
}
process::exit(1);
} else if target.clone() == "-" {
// Read from pipe (stdin)
use_stdin = true;
// Default target URL to empty data URL; the user can control it via --base-url
target_url = "data:text/html,"
} else if is_http_url(target.clone()) || is_data_url(target.clone()) {
target_url = target.as_str();
} else if is_file_url(target.clone()) {
target_url = target.as_str();
} else if path.exists() {
if !path.is_file() {
eprintln!("Local target is not a file: {}", original_target);
if !options.silent {
eprintln!("Local target is not a file: {}", original_target);
}
process::exit(1);
}
target.insert_str(0, if cfg!(windows) { "file:///" } else { "file://" });
@@ -94,10 +114,12 @@ fn main() {
// Initialize client
let mut cache = HashMap::new();
let mut header_map = HeaderMap::new();
header_map.insert(
USER_AGENT,
HeaderValue::from_str(&options.user_agent).expect("Invalid User-Agent header specified"),
);
if let Some(user_agent) = &options.user_agent {
header_map.insert(
USER_AGENT,
HeaderValue::from_str(&user_agent).expect("Invalid User-Agent header specified"),
);
}
let timeout: u64 = if options.timeout > 0 {
options.timeout
} else {
@@ -110,37 +132,64 @@ fn main() {
.build()
.expect("Failed to initialize HTTP client");
// At this stage we assume that the base URL is the same as the target URL
base_url = str!(target_url);
// Retrieve target document
if is_file_url(target_url) || is_http_url(target_url) {
match retrieve_asset(
&mut cache,
&client,
target_url,
target_url,
options.silent,
0,
) {
if use_stdin {
dom = html_to_dom(&read_stdin());
} else if is_file_url(target_url) || is_http_url(target_url) {
match retrieve_asset(&mut cache, &client, target_url, target_url, &options, 0) {
Ok((data, final_url, _media_type)) => {
base_url = final_url;
if options.base_url.clone().unwrap_or(str!()).is_empty() {
base_url = final_url
}
dom = html_to_dom(&String::from_utf8_lossy(&data));
}
Err(_) => {
eprintln!("Could not retrieve target document");
if !options.silent {
eprintln!("Could not retrieve target document");
}
process::exit(1);
}
}
} else if is_data_url(target_url) {
let (media_type, data): (String, Vec<u8>) = data_url_to_data(target_url);
let (media_type, data): (String, Vec<u8>) = parse_data_url(target_url);
if !media_type.eq_ignore_ascii_case("text/html") {
eprintln!("Unsupported data URL media type");
if !options.silent {
eprintln!("Unsupported data URL media type");
}
process::exit(1);
}
base_url = str!(target_url);
dom = html_to_dom(&String::from_utf8_lossy(&data));
} else {
process::exit(1);
}
// Use custom base URL if specified, read and use what's in the DOM otherwise
if !options.base_url.clone().unwrap_or(str!()).is_empty() {
if is_data_url(options.base_url.clone().unwrap()) {
if !options.silent {
eprintln!("Data URLs cannot be used as base URL");
}
process::exit(1);
} else {
base_url = options.base_url.clone().unwrap();
}
} else {
if let Some(existing_base_url) = get_base_url(&dom.document) {
base_url = resolve_url(target_url, existing_base_url).unwrap();
}
}
// Embed remote assets
walk_and_embed_assets(&mut cache, &client, &base_url, &dom.document, &options, 0);
// Update or add new BASE tag to reroute network requests and hash-links in the final document
if let Some(new_base_url) = options.base_url.clone() {
dom = set_base_url(&dom.document, new_base_url);
}
// Request and embed /favicon.ico (unless it's already linked in the document)
if !options.no_images && is_http_url(target_url) && !has_favicon(&dom.document) {
let favicon_ico_url: String = resolve_url(&base_url, "/favicon.ico").unwrap();
@@ -150,7 +199,7 @@ fn main() {
&client,
&base_url,
&favicon_ico_url,
options.silent,
&options,
0,
) {
Ok((data, final_url, media_type)) => {
@@ -163,15 +212,12 @@ fn main() {
}
}
// Embed remote assets
walk_and_embed_assets(&mut cache, &client, &base_url, &dom.document, &options, 0);
// Serialize DOM tree
let mut result: String = stringify_document(&dom.document, &options);
// Add metadata tag
if !options.no_metadata {
let metadata_comment = metadata_tag(&base_url);
let metadata_comment: String = create_metadata_tag(&target_url);
result.insert_str(0, &metadata_comment);
if metadata_comment.len() > 0 {
result.insert_str(metadata_comment.len(), "\n");

View File

@@ -1,23 +1,29 @@
use clap::{App, Arg};
use std::env;
#[derive(Default)]
pub struct Options {
pub target: String,
pub no_audio: bool,
pub base_url: Option<String>,
pub no_css: bool,
pub no_fonts: bool,
pub ignore_errors: bool,
pub no_frames: bool,
pub no_fonts: bool,
pub no_images: bool,
pub isolate: bool,
pub no_js: bool,
pub insecure: bool,
pub isolate: bool,
pub no_metadata: bool,
pub output: String,
pub silent: bool,
pub timeout: u64,
pub user_agent: String,
pub no_metadata: bool,
pub user_agent: Option<String>,
pub no_video: bool,
pub target: String,
pub no_color: bool,
}
const ASCII: &str = " \
const ASCII: &'static str = " \
_____ ______________ __________ ___________________ ___
| \\ / \\ | | | | | |
| \\_/ __ \\_| __ | | ___ ___ |__| |
@@ -27,36 +33,40 @@ const ASCII: &str = " \
|___| |__________| \\_____________________| |___| |___| |___|
";
const DEFAULT_NETWORK_TIMEOUT: u64 = 120;
const DEFAULT_USER_AGENT: &str =
const DEFAULT_USER_AGENT: &'static str =
"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:73.0) Gecko/20100101 Firefox/73.0";
const ENV_VAR_NO_COLOR: &str = "NO_COLOR";
const ENV_VAR_TERM: &str = "TERM";
impl Options {
pub fn from_args() -> Options {
let app = App::new(env!("CARGO_PKG_NAME"))
.version(crate_version!())
.author(crate_authors!("\n"))
.author(format!("\n{}", crate_authors!("\n")).as_str())
.about(format!("{}\n{}", ASCII, crate_description!()).as_str())
.arg(
Arg::with_name("target")
.required(true)
.takes_value(true)
.index(1)
.help("URL or file path"),
)
// .args_from_usage("-a, --no-audio 'Removes audio sources'")
.args_from_usage("-a, --no-audio 'Removes audio sources'")
.args_from_usage("-b, --base-url=[http://localhost/] 'Sets custom base URL'")
.args_from_usage("-c, --no-css 'Removes CSS'")
.args_from_usage("-e, --ignore-errors 'Ignore network errors'")
.args_from_usage("-f, --no-frames 'Removes frames and iframes'")
.args_from_usage("-F, --no-fonts 'Removes fonts'")
.args_from_usage("-i, --no-images 'Removes images'")
.args_from_usage("-I, --isolate 'Cuts off document from the Internet'")
.args_from_usage("-j, --no-js 'Removes JavaScript'")
.args_from_usage("-k, --insecure 'Allows invalid X.509 (TLS) certificates'")
.args_from_usage("-M, --no-metadata 'Excludes metadata information from the document'")
.args_from_usage("-o, --output=[document.html] 'Write output to <file>'")
.args_from_usage("-M, --no-metadata 'Excludes timestamp and source information'")
.args_from_usage("-o, --output=[document.html] 'Writes output to <file>'")
.args_from_usage("-s, --silent 'Suppresses verbosity'")
.args_from_usage("-t, --timeout=[60] 'Adjust network request timeout'")
.args_from_usage("-u, --user-agent=[Firefox] 'Set custom User-Agent string'")
// .args_from_usage("-v, --no-video 'Removes video sources'")
.args_from_usage("-t, --timeout=[60] 'Adjusts network request timeout'")
.args_from_usage("-u, --user-agent=[Firefox] 'Sets custom User-Agent string'")
.args_from_usage("-v, --no-video 'Removes video sources'")
.arg(
Arg::with_name("target")
.required(true)
.takes_value(true)
.index(1)
.help("URL or file path, use - for stdin"),
)
.get_matches();
let mut options: Options = Options::default();
@@ -65,7 +75,12 @@ impl Options {
.value_of("target")
.expect("please set target")
.to_string();
options.no_audio = app.is_present("no-audio");
if let Some(base_url) = app.value_of("base-url") {
options.base_url = Some(str!(base_url));
}
options.no_css = app.is_present("no-css");
options.ignore_errors = app.is_present("ignore-errors");
options.no_frames = app.is_present("no-frames");
options.no_fonts = app.is_present("no-fonts");
options.no_images = app.is_present("no-images");
@@ -80,10 +95,20 @@ impl Options {
.unwrap_or(&DEFAULT_NETWORK_TIMEOUT.to_string())
.parse::<u64>()
.unwrap();
options.user_agent = app
.value_of("user-agent")
.unwrap_or(DEFAULT_USER_AGENT)
.to_string();
if let Some(user_agent) = app.value_of("user-agent") {
options.user_agent = Some(str!(user_agent));
} else {
options.user_agent = Some(DEFAULT_USER_AGENT.to_string());
}
options.no_video = app.is_present("no-video");
options.no_color =
env::var_os(ENV_VAR_NO_COLOR).is_some() || atty::isnt(atty::Stream::Stderr);
if let Some(term) = env::var_os(ENV_VAR_TERM) {
if term == "dumb" {
options.no_color = true;
}
}
options
}

123
src/tests/cli/base_url.rs Normal file
View File

@@ -0,0 +1,123 @@
// ██████╗ █████╗ ███████╗███████╗██╗███╗ ██╗ ██████╗
// ██╔══██╗██╔══██╗██╔════╝██╔════╝██║████╗ ██║██╔════╝
// ██████╔╝███████║███████╗███████╗██║██╔██╗ ██║██║ ███╗
// ██╔═══╝ ██╔══██║╚════██║╚════██║██║██║╚██╗██║██║ ██║
// ██║ ██║ ██║███████║███████║██║██║ ╚████║╚██████╔╝
// ╚═╝ ╚═╝ ╚═╝╚══════╝╚══════╝╚═╝╚═╝ ╚═══╝ ╚═════╝
#[cfg(test)]
mod passing {
use assert_cmd::prelude::*;
use std::env;
use std::process::Command;
#[test]
fn add_new_when_provided() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-b")
.arg("http://localhost:8000/")
.arg("data:text/html,Hello%2C%20World!")
.output()
.unwrap();
// STDOUT should contain newly added base URL
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head>\
<base href=\"http://localhost:8000/\"></base>\
</head><body>Hello, World!</body></html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn keep_existing_when_none_provided() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("data:text/html,<base href=\"http://localhost:8000/\" />Hello%2C%20World!")
.output()
.unwrap();
// STDOUT should contain newly added base URL
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head>\
<base href=\"http://localhost:8000/\">\
</head><body>Hello, World!</body></html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn override_existing_when_provided() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-b")
.arg("http://localhost/")
.arg("data:text/html,<base href=\"http://localhost:8000/\" />Hello%2C%20World!")
.output()
.unwrap();
// STDOUT should contain newly added base URL
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head>\
<base href=\"http://localhost/\">\
</head><body>Hello, World!</body></html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn remove_existing_when_empty_provided() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-b")
.arg("")
.arg("data:text/html,<base href=\"http://localhost:8000/\" />Hello%2C%20World!")
.output()
.unwrap();
// STDOUT should contain newly added base URL
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head>\
<base href=\"\">\
</head><body>Hello, World!</body></html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
}

145
src/tests/cli/basic.rs Normal file
View File

@@ -0,0 +1,145 @@
// ██████╗ █████╗ ███████╗███████╗██╗███╗ ██╗ ██████╗
// ██╔══██╗██╔══██╗██╔════╝██╔════╝██║████╗ ██║██╔════╝
// ██████╔╝███████║███████╗███████╗██║██╔██╗ ██║██║ ███╗
// ██╔═══╝ ██╔══██║╚════██║╚════██║██║██║╚██╗██║██║ ██║
// ██║ ██║ ██║███████║███████║██║██║ ╚████║╚██████╔╝
// ╚═╝ ╚═╝ ╚═╝╚══════╝╚══════╝╚═╝╚═╝ ╚═══╝ ╚═════╝
#[cfg(test)]
mod passing {
use assert_cmd::prelude::*;
use std::env;
use std::io::Write;
use std::process::{Command, Stdio};
use tempfile::NamedTempFile;
#[test]
fn print_version() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd.arg("-V").output().unwrap();
// STDOUT should contain program name and version
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
format!("{} {}\n", env!("CARGO_PKG_NAME"), env!("CARGO_PKG_VERSION"))
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn stdin_target_input() -> Result<(), Box<dyn std::error::Error>> {
let mut echo = Command::new("echo")
.arg("Hello from STDIN")
.stdout(Stdio::piped())
.spawn()
.unwrap();
let echo_out = echo.stdout.take().unwrap();
echo.wait().unwrap();
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
cmd.stdin(echo_out);
let out = cmd.arg("-M").arg("-").output().unwrap();
// STDOUT should contain HTML from STDIN
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head></head><body>Hello from STDIN\n</body></html>\n"
);
Ok(())
}
#[test]
fn css_import_string() -> Result<(), Box<dyn std::error::Error>> {
let file_url_prefix: &str = if cfg!(windows) { "file:///" } else { "file://" };
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let mut file_css = NamedTempFile::new()?;
writeln!(file_css, "body{{background-color:#000;color:#fff}}")?;
let mut file_html = NamedTempFile::new()?;
writeln!(
file_html,
"\
<style>\n\
@charset 'UTF-8';\n\
\n\
@import '{file}{css_path}';\n\
\n\
@import url({file}{css_path});\n\
\n\
@import url('{file}{css_path}')\n\
</style>\n\
",
file = file_url_prefix,
css_path = str!(file_css.path().to_str().unwrap()).replace("\\", "/"),
)?;
let out = cmd.arg("-M").arg(file_html.path()).output().unwrap();
// STDOUT should contain embedded CSS url()'s
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head><style>\n@charset 'UTF-8';\n\n@import 'data:text/css;base64,Ym9keXtiYWNrZ3JvdW5kLWNvbG9yOiMwMDA7Y29sb3I6I2ZmZn0K';\n\n@import url('data:text/css;base64,Ym9keXtiYWNrZ3JvdW5kLWNvbG9yOiMwMDA7Y29sb3I6I2ZmZn0K');\n\n@import url('data:text/css;base64,Ym9keXtiYWNrZ3JvdW5kLWNvbG9yOiMwMDA7Y29sb3I6I2ZmZn0K')\n</style>\n\n</head><body></body></html>\n"
);
// STDERR should list temporary files that got retrieved
assert_eq!(
std::str::from_utf8(&out.stderr).unwrap(),
format!(
"\
{file}{html_path}\n \
{file}{css_path}\n \
{file}{css_path}\n \
{file}{css_path}\n\
",
file = file_url_prefix,
html_path = str!(file_html.path().to_str().unwrap()).replace("\\", "/"),
css_path = str!(file_css.path().to_str().unwrap()).replace("\\", "/"),
)
);
// The exit code should be 0
out.assert().code(0);
Ok(())
}
}
// ███████╗ █████╗ ██╗██╗ ██╗███╗ ██╗ ██████╗
// ██╔════╝██╔══██╗██║██║ ██║████╗ ██║██╔════╝
// █████╗ ███████║██║██║ ██║██╔██╗ ██║██║ ███╗
// ██╔══╝ ██╔══██║██║██║ ██║██║╚██╗██║██║ ██║
// ██║ ██║ ██║██║███████╗██║██║ ╚████║╚██████╔╝
// ╚═╝ ╚═╝ ╚═╝╚═╝╚══════╝╚═╝╚═╝ ╚═══╝ ╚═════╝
#[cfg(test)]
mod failing {
use assert_cmd::prelude::*;
use std::env;
use std::process::Command;
#[test]
fn bad_input_empty_target() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd.arg("").output().unwrap();
// STDOUT should be empty
assert_eq!(std::str::from_utf8(&out.stdout).unwrap(), "");
// STDERR should contain error description
assert_eq!(
std::str::from_utf8(&out.stderr).unwrap(),
"No target specified\n"
);
// The exit code should be 1
out.assert().code(1);
Ok(())
}
}

234
src/tests/cli/data_url.rs Normal file
View File

@@ -0,0 +1,234 @@
// ██████╗ █████╗ ███████╗███████╗██╗███╗ ██╗ ██████╗
// ██╔══██╗██╔══██╗██╔════╝██╔════╝██║████╗ ██║██╔════╝
// ██████╔╝███████║███████╗███████╗██║██╔██╗ ██║██║ ███╗
// ██╔═══╝ ██╔══██║╚════██║╚════██║██║██║╚██╗██║██║ ██║
// ██║ ██║ ██║███████║███████║██║██║ ╚████║╚██████╔╝
// ╚═╝ ╚═╝ ╚═╝╚══════╝╚══════╝╚═╝╚═╝ ╚═══╝ ╚═════╝
#[cfg(test)]
mod passing {
use assert_cmd::prelude::*;
use std::env;
use std::process::Command;
#[test]
fn bad_input_data_url() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd.arg("data:,Hello%2C%20World!").output().unwrap();
// STDOUT should contain HTML
assert_eq!(std::str::from_utf8(&out.stdout).unwrap(), "");
// STDERR should contain error description
assert_eq!(
std::str::from_utf8(&out.stderr).unwrap(),
"Unsupported data URL media type\n"
);
// The exit code should be 1
out.assert().code(1);
Ok(())
}
#[test]
fn isolate_data_url() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-I")
.arg("data:text/html,Hello%2C%20World!")
.output()
.unwrap();
// STDOUT should contain isolated HTML
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head>\
<meta http-equiv=\"Content-Security-Policy\" content=\"default-src 'unsafe-inline' data:;\"></meta>\
</head><body>Hello, World!</body></html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn remove_css_from_data_url() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-c")
.arg("data:text/html,<style>body{background-color:pink}</style>Hello")
.output()
.unwrap();
// STDOUT should contain HTML with no CSS
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head>\
<meta http-equiv=\"Content-Security-Policy\" content=\"style-src 'none';\"></meta>\
<style></style>\
</head><body>Hello</body></html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn remove_fonts_from_data_url() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-F")
.arg("data:text/html,<style>@font-face { font-family: myFont; src: url(font.woff); }</style>Hi")
.output()
.unwrap();
// STDOUT should contain HTML with no web fonts
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head>\
<meta http-equiv=\"Content-Security-Policy\" content=\"font-src 'none';\"></meta>\
<style></style>\
</head><body>Hi</body></html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn remove_frames_from_data_url() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-f")
.arg("data:text/html,<iframe src=\"https://duckduckgo.com\"></iframe>Hi")
.output()
.unwrap();
// STDOUT should contain HTML with no iframes
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head>\
<meta http-equiv=\"Content-Security-Policy\" content=\"frame-src 'none'; child-src 'none';\"></meta>\
</head><body><iframe src=\"\"></iframe>Hi</body></html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn remove_images_from_data_url() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-i")
.arg("data:text/html,<img src=\"https://google.com\"/>Hi")
.output()
.unwrap();
// STDOUT should contain HTML with no images
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
format!(
"<html>\
<head>\
<meta http-equiv=\"Content-Security-Policy\" content=\"img-src data:;\"></meta>\
</head>\
<body>\
<img src=\"{empty_image}\">\
Hi\
</body>\
</html>\n",
empty_image = empty_image!()
)
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn remove_js_from_data_url() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-j")
.arg("data:text/html,<script>alert(2)</script>Hi")
.output()
.unwrap();
// STDOUT should contain HTML with no JS
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html>\
<head>\
<meta http-equiv=\"Content-Security-Policy\" content=\"script-src 'none';\"></meta>\
<script></script></head>\
<body>Hi</body>\
</html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn security_disallow_local_assets_within_data_url_targets(
) -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("data:text/html,%3Cscript%20src=\"src/tests/data/basic/local-script.js\"%3E%3C/script%3E")
.output()
.unwrap();
// STDOUT should contain HTML with no JS in it
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head><script></script></head><body></body></html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
}

View File

@@ -13,242 +13,6 @@ mod passing {
use std::process::Command;
use tempfile::NamedTempFile;
#[test]
fn print_version() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd.arg("-V").output().unwrap();
// STDOUT should contain program name and version
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
format!("{} {}\n", env!("CARGO_PKG_NAME"), env!("CARGO_PKG_VERSION"))
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn bad_input_empty_target() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd.arg("").output().unwrap();
// STDOUT should be empty
assert_eq!(std::str::from_utf8(&out.stdout).unwrap(), "");
// STDERR should contain error description
assert_eq!(
std::str::from_utf8(&out.stderr).unwrap(),
"No target specified\n"
);
// The exit code should be 1
out.assert().code(1);
Ok(())
}
#[test]
fn bad_input_data_url() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd.arg("data:,Hello%2C%20World!").output().unwrap();
// STDOUT should contain HTML
assert_eq!(std::str::from_utf8(&out.stdout).unwrap(), "");
// STDERR should contain error description
assert_eq!(
std::str::from_utf8(&out.stderr).unwrap(),
"Unsupported data URL media type\n"
);
// The exit code should be 1
out.assert().code(1);
Ok(())
}
#[test]
fn isolate_data_url() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-I")
.arg("data:text/html,Hello%2C%20World!")
.output()
.unwrap();
// STDOUT should contain isolated HTML
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head>\
<meta http-equiv=\"Content-Security-Policy\" content=\"default-src 'unsafe-inline' data:;\"></meta>\
</head><body>Hello, World!</body></html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn remove_css_from_data_url() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-c")
.arg("data:text/html,<style>body{background-color:pink}</style>Hello")
.output()
.unwrap();
// STDOUT should contain HTML with no CSS
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head>\
<meta http-equiv=\"Content-Security-Policy\" content=\"style-src 'none';\"></meta>\
<style></style>\
</head><body>Hello</body></html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn remove_fonts_from_data_url() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-F")
.arg("data:text/html,<style>@font-face { font-family: myFont; src: url(font.woff); }</style>Hi")
.output()
.unwrap();
// STDOUT should contain HTML with no web fonts
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head>\
<meta http-equiv=\"Content-Security-Policy\" content=\"font-src 'none';\"></meta>\
<style></style>\
</head><body>Hi</body></html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn remove_frames_from_data_url() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-f")
.arg("data:text/html,<iframe src=\"https://duckduckgo.com\"></iframe>Hi")
.output()
.unwrap();
// STDOUT should contain HTML with no iframes
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head>\
<meta http-equiv=\"Content-Security-Policy\" content=\"frame-src 'none'; child-src 'none';\"></meta>\
</head><body><iframe src=\"\"></iframe>Hi</body></html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn remove_images_from_data_url() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-i")
.arg("data:text/html,<img src=\"https://google.com\"/>Hi")
.output()
.unwrap();
// STDOUT should contain HTML with no images
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
format!(
"<html>\
<head>\
<meta http-equiv=\"Content-Security-Policy\" content=\"img-src data:;\"></meta>\
</head>\
<body>\
<img src=\"{empty_image}\">\
Hi\
</body>\
</html>\n",
empty_image = empty_image!()
)
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn remove_js_from_data_url() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("-j")
.arg("data:text/html,<script>alert(2)</script>Hi")
.output()
.unwrap();
// STDOUT should contain HTML with no JS
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html>\
<head>\
<meta http-equiv=\"Content-Security-Policy\" content=\"script-src 'none';\"></meta>\
<script></script></head>\
<body>Hi</body>\
</html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn local_file_target_input() -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
@@ -305,8 +69,7 @@ mod passing {
#[test]
fn local_file_target_input_absolute_target_path() -> Result<(), Box<dyn std::error::Error>> {
let cwd = env::current_dir().unwrap();
let cwd_normalized: String =
str!(env::current_dir().unwrap().to_str().unwrap()).replace("\\", "/");
let cwd_normalized: String = str!(cwd.to_str().unwrap()).replace("\\", "/");
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
@@ -337,7 +100,7 @@ mod passing {
<title>Local HTML file</title>\n \
<link rel=\"stylesheet\" type=\"text/css\">\n \
<link rel=\"stylesheet\" type=\"text/css\">\n</head>\n\n<body>\n \
<img alt=\"\" src=\"{empty_image}\">\n \
<img src=\"{empty_image}\" alt=\"\">\n \
<a href=\"file://local-file.html/\">Tricky href</a>\n \
<a href=\"https://github.com/Y2Z/monolith\">Remote URL</a>\n \
<script></script>\n\n\n\n\
@@ -399,7 +162,7 @@ mod passing {
<title>Local HTML file</title>\n \
<link rel=\"stylesheet\" type=\"text/css\">\n \
<link rel=\"stylesheet\" type=\"text/css\">\n</head>\n\n<body>\n \
<img alt=\"\" src=\"{empty_image}\">\n \
<img src=\"{empty_image}\" alt=\"\">\n \
<a href=\"file://local-file.html/\">Tricky href</a>\n \
<a href=\"https://github.com/Y2Z/monolith\">Remote URL</a>\n \
<script></script>\n\n\n\n\
@@ -433,31 +196,6 @@ mod passing {
Ok(())
}
#[test]
fn security_disallow_local_assets_within_data_url_targets(
) -> Result<(), Box<dyn std::error::Error>> {
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg("data:text/html,%3Cscript%20src=\"src/tests/data/basic/local-script.js\"%3E%3C/script%3E")
.output()
.unwrap();
// STDOUT should contain HTML with no JS in it
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head><script></script></head><body></body></html>\n"
);
// STDERR should be empty
assert_eq!(std::str::from_utf8(&out.stderr).unwrap(), "");
// The exit code should be 0
out.assert().code(0);
Ok(())
}
#[test]
fn embed_file_url_local_asset_within_style_attribute() -> Result<(), Box<dyn std::error::Error>>
{
@@ -503,57 +241,4 @@ mod passing {
Ok(())
}
#[test]
fn css_import_string() -> Result<(), Box<dyn std::error::Error>> {
let file_url_prefix: &str = if cfg!(windows) { "file:///" } else { "file://" };
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let mut file_css = NamedTempFile::new()?;
writeln!(file_css, "body{{background-color:#000;color:#fff}}")?;
let mut file_html = NamedTempFile::new()?;
writeln!(
file_html,
"\
<style>\n\
@charset 'UTF-8';\n\
\n\
@import '{file}{css_path}';\n\
\n\
@import url({file}{css_path});\n\
\n\
@import url('{file}{css_path}')\n\
</style>\n\
",
file = file_url_prefix,
css_path = str!(file_css.path().to_str().unwrap()).replace("\\", "/"),
)?;
let out = cmd.arg("-M").arg(file_html.path()).output().unwrap();
// STDOUT should contain embedded CSS url()'s
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head><style>\n@charset 'UTF-8';\n\n@import 'data:text/css;base64,Ym9keXtiYWNrZ3JvdW5kLWNvbG9yOiMwMDA7Y29sb3I6I2ZmZn0K';\n\n@import url('data:text/css;base64,Ym9keXtiYWNrZ3JvdW5kLWNvbG9yOiMwMDA7Y29sb3I6I2ZmZn0K');\n\n@import url('data:text/css;base64,Ym9keXtiYWNrZ3JvdW5kLWNvbG9yOiMwMDA7Y29sb3I6I2ZmZn0K')\n</style>\n\n</head><body></body></html>\n"
);
// STDERR should list temporary files that got retrieved
assert_eq!(
std::str::from_utf8(&out.stderr).unwrap(),
format!(
"\
{file}{html_path}\n \
{file}{css_path}\n \
{file}{css_path}\n \
{file}{css_path}\n\
",
file = file_url_prefix,
html_path = str!(file_html.path().to_str().unwrap()).replace("\\", "/"),
css_path = str!(file_css.path().to_str().unwrap()).replace("\\", "/"),
)
);
// The exit code should be 0
out.assert().code(0);
Ok(())
}
}

5
src/tests/cli/mod.rs Normal file
View File

@@ -0,0 +1,5 @@
mod base_url;
mod basic;
mod data_url;
mod local_files;
mod unusual_encodings;

View File

@@ -0,0 +1,51 @@
// ██████╗ █████╗ ███████╗███████╗██╗███╗ ██╗ ██████╗
// ██╔══██╗██╔══██╗██╔════╝██╔════╝██║████╗ ██║██╔════╝
// ██████╔╝███████║███████╗███████╗██║██╔██╗ ██║██║ ███╗
// ██╔═══╝ ██╔══██║╚════██║╚════██║██║██║╚██╗██║██║ ██║
// ██║ ██║ ██║███████║███████║██║██║ ╚████║╚██████╔╝
// ╚═╝ ╚═╝ ╚═╝╚══════╝╚══════╝╚═╝╚═╝ ╚═══╝ ╚═════╝
#[cfg(test)]
mod passing {
use assert_cmd::prelude::*;
use std::env;
use std::process::Command;
#[test]
fn change_encoding_to_utf_8() -> Result<(), Box<dyn std::error::Error>> {
let cwd = env::current_dir().unwrap();
let cwd_normalized: String = str!(cwd.to_str().unwrap()).replace("\\", "/");
let mut cmd = Command::cargo_bin(env!("CARGO_PKG_NAME"))?;
let out = cmd
.arg("-M")
.arg(if cfg!(windows) {
"src\\tests\\data\\unusual_encodings\\iso-8859-1.html"
} else {
"src/tests/data/unusual_encodings/iso-8859-1.html"
})
.output()
.unwrap();
let file_url_protocol: &str = if cfg!(windows) { "file:///" } else { "file://" };
// STDOUT should contain newly added base URL
assert_eq!(
std::str::from_utf8(&out.stdout).unwrap(),
"<html><head>\n <meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\">\n </head>\n <body>\n © Some Company\n \n\n</body></html>\n"
);
// STDERR should contain only the target file
assert_eq!(
std::str::from_utf8(&out.stderr).unwrap(),
format!(
"{file}{cwd}/src/tests/data/unusual_encodings/iso-8859-1.html\n",
file = file_url_protocol,
cwd = cwd_normalized,
)
);
// The exit code should be 0
out.assert().code(0);
Ok(())
}
}

View File

@@ -0,0 +1,8 @@
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
</head>
<body>
&copy; Some Company
</body>
</html>

View File

@@ -11,7 +11,7 @@ mod passing {
#[test]
fn empty_input_sha256() {
assert!(html::has_proper_integrity(
assert!(html::check_integrity(
"".as_bytes(),
"sha256-47DEQpj8HBSa+/TImW+5JCeuQeRkm5NMpJWZG3hSuFU="
));
@@ -19,7 +19,7 @@ mod passing {
#[test]
fn sha256() {
assert!(html::has_proper_integrity(
assert!(html::check_integrity(
"abcdef0123456789".as_bytes(),
"sha256-9EWAHgy4mSYsm54hmDaIDXPKLRsLnBX7lZyQ6xISNOM="
));
@@ -27,7 +27,7 @@ mod passing {
#[test]
fn sha384() {
assert!(html::has_proper_integrity(
assert!(html::check_integrity(
"abcdef0123456789".as_bytes(),
"sha384-gc9l7omltke8C33bedgh15E12M7RrAQa5t63Yb8APlpe7ZhiqV23+oqiulSJl3Kw"
));
@@ -35,7 +35,7 @@ mod passing {
#[test]
fn sha512() {
assert!(html::has_proper_integrity(
assert!(html::check_integrity(
"abcdef0123456789".as_bytes(),
"sha512-zG5B88cYMqcdiMi9gz0XkOFYw2BpjeYdn5V6+oFrMgSNjRpqL7EF8JEwl17ztZbK3N7I/tTwp3kxQbN1RgFBww=="
));
@@ -55,20 +55,17 @@ mod failing {
#[test]
fn empty_hash() {
assert!(!html::has_proper_integrity(
"abcdef0123456789".as_bytes(),
""
));
assert!(!html::check_integrity("abcdef0123456789".as_bytes(), ""));
}
#[test]
fn empty_input_empty_hash() {
assert!(!html::has_proper_integrity("".as_bytes(), ""));
assert!(!html::check_integrity("".as_bytes(), ""));
}
#[test]
fn sha256() {
assert!(!html::has_proper_integrity(
assert!(!html::check_integrity(
"abcdef0123456789".as_bytes(),
"sha256-badhash"
));
@@ -76,7 +73,7 @@ mod failing {
#[test]
fn sha384() {
assert!(!html::has_proper_integrity(
assert!(!html::check_integrity(
"abcdef0123456789".as_bytes(),
"sha384-badhash"
));
@@ -84,7 +81,7 @@ mod failing {
#[test]
fn sha512() {
assert!(!html::has_proper_integrity(
assert!(!html::check_integrity(
"abcdef0123456789".as_bytes(),
"sha512-badhash"
));

View File

@@ -14,7 +14,7 @@ mod passing {
fn isolated() {
let mut options = Options::default();
options.isolate = true;
let csp_content = html::csp(&options);
let csp_content = html::compose_csp(&options);
assert_eq!(csp_content, "default-src 'unsafe-inline' data:;");
}
@@ -23,7 +23,7 @@ mod passing {
fn no_css() {
let mut options = Options::default();
options.no_css = true;
let csp_content = html::csp(&options);
let csp_content = html::compose_csp(&options);
assert_eq!(csp_content, "style-src 'none';");
}
@@ -32,7 +32,7 @@ mod passing {
fn no_fonts() {
let mut options = Options::default();
options.no_fonts = true;
let csp_content = html::csp(&options);
let csp_content = html::compose_csp(&options);
assert_eq!(csp_content, "font-src 'none';");
}
@@ -41,7 +41,7 @@ mod passing {
fn no_frames() {
let mut options = Options::default();
options.no_frames = true;
let csp_content = html::csp(&options);
let csp_content = html::compose_csp(&options);
assert_eq!(csp_content, "frame-src 'none'; child-src 'none';");
}
@@ -50,7 +50,7 @@ mod passing {
fn no_js() {
let mut options = Options::default();
options.no_js = true;
let csp_content = html::csp(&options);
let csp_content = html::compose_csp(&options);
assert_eq!(csp_content, "script-src 'none';");
}
@@ -59,7 +59,7 @@ mod passing {
fn no_images() {
let mut options = Options::default();
options.no_images = true;
let csp_content = html::csp(&options);
let csp_content = html::compose_csp(&options);
assert_eq!(csp_content, "img-src data:;");
}
@@ -73,7 +73,7 @@ mod passing {
options.no_frames = true;
options.no_js = true;
options.no_images = true;
let csp_content = html::csp(&options);
let csp_content = html::compose_csp(&options);
assert_eq!(csp_content, "default-src 'unsafe-inline' data:; style-src 'none'; font-src 'none'; frame-src 'none'; child-src 'none'; script-src 'none'; img-src data:;");
}

View File

@@ -15,7 +15,7 @@ mod passing {
fn http_url() {
let url = "http://192.168.1.1/";
let timestamp = Utc::now().to_rfc3339_opts(SecondsFormat::Secs, true);
let metadata_comment: String = html::metadata_tag(url);
let metadata_comment: String = html::create_metadata_tag(url);
assert_eq!(
metadata_comment,
@@ -33,7 +33,7 @@ mod passing {
fn file_url() {
let url = "file:///home/monolith/index.html";
let timestamp = Utc::now().to_rfc3339_opts(SecondsFormat::Secs, true);
let metadata_comment: String = html::metadata_tag(url);
let metadata_comment: String = html::create_metadata_tag(url);
assert_eq!(
metadata_comment,
@@ -50,7 +50,7 @@ mod passing {
fn data_url() {
let url = "data:text/html,Hello%2C%20World!";
let timestamp = Utc::now().to_rfc3339_opts(SecondsFormat::Secs, true);
let metadata_comment: String = html::metadata_tag(url);
let metadata_comment: String = html::create_metadata_tag(url);
assert_eq!(
metadata_comment,
@@ -77,6 +77,6 @@ mod failing {
#[test]
fn empty_string() {
assert_eq!(html::metadata_tag(""), "");
assert_eq!(html::create_metadata_tag(""), "");
}
}

View File

@@ -14,18 +14,108 @@ mod passing {
use crate::opts::Options;
#[test]
fn replace_with_empty_images() {
fn small_medium_large() {
let cache = &mut HashMap::new();
let client = Client::new();
let srcset_value = "small.png 1x, large.png 2x";
let srcset_value = "small.png 1x, medium.png 1.5x, large.png 2x";
let mut options = Options::default();
options.no_images = true;
options.silent = true;
let embedded_css = html::embed_srcset(cache, &client, "", &srcset_value, &options, 0);
assert_eq!(
embedded_css,
format!(
"{} 1x, {} 1.5x, {} 2x",
empty_image!(),
empty_image!(),
empty_image!(),
),
);
}
#[test]
fn small_medium_only_medium_has_scale() {
let cache = &mut HashMap::new();
let client = Client::new();
let srcset_value = "small.png, medium.png 1.5x";
let mut options = Options::default();
options.no_images = true;
options.silent = true;
let embedded_css = html::embed_srcset(cache, &client, "", &srcset_value, &options, 0);
assert_eq!(
embedded_css,
format!("{}, {} 1.5x", empty_image!(), empty_image!()),
);
}
#[test]
fn commas_within_file_names() {
let cache = &mut HashMap::new();
let client = Client::new();
let srcset_value = "small,s.png 1x, large,l.png 2x";
let mut options = Options::default();
options.no_images = true;
options.silent = true;
let embedded_css = html::embed_srcset(cache, &client, "", &srcset_value, &options, 0);
assert_eq!(
embedded_css,
format!("{} 1x, {} 2x", empty_image!(), empty_image!()),
embedded_css
);
}
#[test]
fn tabs_and_newlines_after_commas() {
let cache = &mut HashMap::new();
let client = Client::new();
let srcset_value = "small,s.png 1x,\nmedium,m.png 2x,\nlarge,l.png 3x";
let mut options = Options::default();
options.no_images = true;
options.silent = true;
let embedded_css = html::embed_srcset(cache, &client, "", &srcset_value, &options, 0);
assert_eq!(
embedded_css,
format!(
"{} 1x, {} 2x, {} 3x",
empty_image!(),
empty_image!(),
empty_image!()
),
);
}
}
// ███████╗ █████╗ ██╗██╗ ██╗███╗ ██╗ ██████╗
// ██╔════╝██╔══██╗██║██║ ██║████╗ ██║██╔════╝
// █████╗ ███████║██║██║ ██║██╔██╗ ██║██║ ███╗
// ██╔══╝ ██╔══██║██║██║ ██║██║╚██╗██║██║ ██║
// ██║ ██║ ██║██║███████╗██║██║ ╚████║╚██████╔╝
// ╚═╝ ╚═╝ ╚═╝╚═╝╚══════╝╚═╝╚═╝ ╚═══╝ ╚═════╝
#[cfg(test)]
mod failing {
use reqwest::blocking::Client;
use std::collections::HashMap;
use crate::html;
use crate::opts::Options;
#[test]
fn trailing_comma() {
let cache = &mut HashMap::new();
let client = Client::new();
let srcset_value = "small.png 1x, large.png 2x,";
let mut options = Options::default();
options.no_images = true;
options.silent = true;
let embedded_css = html::embed_srcset(cache, &client, "", &srcset_value, &options, 0);
assert_eq!(
embedded_css,
format!("{} 1x, {} 2x,", empty_image!(), empty_image!()),
);
}
}

View File

@@ -0,0 +1,104 @@
// ██████╗ █████╗ ███████╗███████╗██╗███╗ ██╗ ██████╗
// ██╔══██╗██╔══██╗██╔════╝██╔════╝██║████╗ ██║██╔════╝
// ██████╔╝███████║███████╗███████╗██║██╔██╗ ██║██║ ███╗
// ██╔═══╝ ██╔══██║╚════██║╚════██║██║██║╚██╗██║██║ ██║
// ██║ ██║ ██║███████║███████║██║██║ ╚████║╚██████╔╝
// ╚═╝ ╚═╝ ╚═╝╚══════╝╚══════╝╚═╝╚═╝ ╚═══╝ ╚═════╝
#[cfg(test)]
mod passing {
use crate::html;
#[test]
fn present() {
let html = "<!doctype html>
<html>
<head>
<base href=\"https://musicbrainz.org\" />
</head>
<body>
</body>
</html>";
let dom = html::html_to_dom(&html);
assert_eq!(
html::get_base_url(&dom.document),
Some(str!("https://musicbrainz.org"))
);
}
#[test]
fn multiple_tags() {
let html = "<!doctype html>
<html>
<head>
<base href=\"https://www.discogs.com/\" />
<base href=\"https://musicbrainz.org\" />
</head>
<body>
</body>
</html>";
let dom = html::html_to_dom(&html);
assert_eq!(
html::get_base_url(&dom.document),
Some(str!("https://www.discogs.com/"))
);
}
}
// ███████╗ █████╗ ██╗██╗ ██╗███╗ ██╗ ██████╗
// ██╔════╝██╔══██╗██║██║ ██║████╗ ██║██╔════╝
// █████╗ ███████║██║██║ ██║██╔██╗ ██║██║ ███╗
// ██╔══╝ ██╔══██║██║██║ ██║██║╚██╗██║██║ ██║
// ██║ ██║ ██║██║███████╗██║██║ ╚████║╚██████╔╝
// ╚═╝ ╚═╝ ╚═╝╚═╝╚══════╝╚═╝╚═╝ ╚═══╝ ╚═════╝
#[cfg(test)]
mod failing {
use crate::html;
#[test]
fn absent() {
let html = "<!doctype html>
<html>
<head>
</head>
<body>
</body>
</html>";
let dom = html::html_to_dom(&html);
assert_eq!(html::get_base_url(&dom.document), None);
}
#[test]
fn no_href() {
let html = "<!doctype html>
<html>
<head>
<base />
</head>
<body>
</body>
</html>";
let dom = html::html_to_dom(&html);
assert_eq!(html::get_base_url(&dom.document), None);
}
#[test]
fn empty_href() {
let html = "<!doctype html>
<html>
<head>
<base href=\"\" />
</head>
<body>
</body>
</html>";
let dom = html::html_to_dom(&html);
assert_eq!(html::get_base_url(&dom.document), Some(str!()));
}
}

View File

@@ -0,0 +1,54 @@
// ██████╗ █████╗ ███████╗███████╗██╗███╗ ██╗ ██████╗
// ██╔══██╗██╔══██╗██╔════╝██╔════╝██║████╗ ██║██╔════╝
// ██████╔╝███████║███████╗███████╗██║██╔██╗ ██║██║ ███╗
// ██╔═══╝ ██╔══██║╚════██║╚════██║██║██║╚██╗██║██║ ██║
// ██║ ██║ ██║███████║███████║██║██║ ╚████║╚██████╔╝
// ╚═╝ ╚═╝ ╚═╝╚══════╝╚══════╝╚═╝╚═╝ ╚═══╝ ╚═════╝
#[cfg(test)]
mod passing {
use html5ever::rcdom::{Handle, NodeData};
use crate::html;
#[test]
fn div_two_style_attributes() {
let html = "<!doctype html><html><head></head><body><DIV STYLE=\"color: blue;\" style=\"display: none;\"></div></body></html>";
let dom = html::html_to_dom(&html);
let mut count = 0;
fn test_walk(node: &Handle, i: &mut i8) {
*i += 1;
match &node.data {
NodeData::Document => {
// Dig deeper
for child in node.children.borrow().iter() {
test_walk(child, &mut *i);
}
}
NodeData::Element { ref name, .. } => {
let node_name = name.local.as_ref().to_string();
if node_name == "body" {
assert_eq!(html::get_node_attr(node, "class"), None);
} else if node_name == "div" {
assert_eq!(
html::get_node_attr(node, "style"),
Some(str!("color: blue;"))
);
}
for child in node.children.borrow().iter() {
test_walk(child, &mut *i);
}
}
_ => (),
};
}
test_walk(&dom.document, &mut count);
assert_eq!(count, 6);
}
}

View File

@@ -12,7 +12,7 @@ mod passing {
use crate::html;
#[test]
fn get_node_name() {
fn parent_node_names() {
let html = "<!doctype html><html><HEAD></HEAD><body><div><P></P></div></body></html>";
let dom = html::html_to_dom(&html);
let mut count = 0;

View File

@@ -8,7 +8,6 @@
#[cfg(test)]
mod passing {
use crate::html;
use crate::opts::Options;
#[test]
fn icon() {
@@ -39,7 +38,6 @@ mod passing {
#[cfg(test)]
mod failing {
use crate::html;
use crate::opts::Options;
#[test]
fn absent() {

View File

@@ -1,10 +1,13 @@
mod add_favicon;
mod csp;
mod check_integrity;
mod compose_csp;
mod create_metadata_tag;
mod embed_srcset;
mod get_base_url;
mod get_node_attr;
mod get_node_name;
mod has_favicon;
mod has_proper_integrity;
mod is_icon;
mod metadata_tag;
mod set_node_attr;
mod stringify_document;
mod walk_and_embed_assets;

View File

@@ -0,0 +1,105 @@
// ██████╗ █████╗ ███████╗███████╗██╗███╗ ██╗ ██████╗
// ██╔══██╗██╔══██╗██╔════╝██╔════╝██║████╗ ██║██╔════╝
// ██████╔╝███████║███████╗███████╗██║██╔██╗ ██║██║ ███╗
// ██╔═══╝ ██╔══██║╚════██║╚════██║██║██║╚██╗██║██║ ██║
// ██║ ██║ ██║███████║███████║██║██║ ╚████║╚██████╔╝
// ╚═╝ ╚═╝ ╚═╝╚══════╝╚══════╝╚═╝╚═╝ ╚═══╝ ╚═════╝
#[cfg(test)]
mod passing {
use html5ever::rcdom::{Handle, NodeData};
use crate::html;
#[test]
fn html_lang_and_body_style() {
let html = "<!doctype html><html lang=\"en\"><head></head><body></body></html>";
let dom = html::html_to_dom(&html);
let mut count = 0;
fn test_walk(node: &Handle, i: &mut i8) {
*i += 1;
match &node.data {
NodeData::Document => {
// Dig deeper
for child in node.children.borrow().iter() {
test_walk(child, &mut *i);
}
}
NodeData::Element { ref name, .. } => {
let node_name = name.local.as_ref().to_string();
if node_name == "html" {
assert_eq!(html::get_node_attr(node, "lang"), Some(str!("en")));
html::set_node_attr(node, "lang", Some(str!("de")));
assert_eq!(html::get_node_attr(node, "lang"), Some(str!("de")));
html::set_node_attr(node, "lang", None);
assert_eq!(html::get_node_attr(node, "lang"), None);
html::set_node_attr(node, "lang", Some(str!("")));
assert_eq!(html::get_node_attr(node, "lang"), Some(str!("")));
} else if node_name == "body" {
assert_eq!(html::get_node_attr(node, "style"), None);
html::set_node_attr(node, "style", Some(str!("display: none;")));
assert_eq!(
html::get_node_attr(node, "style"),
Some(str!("display: none;"))
);
}
for child in node.children.borrow().iter() {
test_walk(child, &mut *i);
}
}
_ => (),
};
}
test_walk(&dom.document, &mut count);
assert_eq!(count, 5);
}
#[test]
fn body_background() {
let html = "<!doctype html><html lang=\"en\"><head></head><body background=\"1\" background=\"2\"></body></html>";
let dom = html::html_to_dom(&html);
let mut count = 0;
fn test_walk(node: &Handle, i: &mut i8) {
*i += 1;
match &node.data {
NodeData::Document => {
// Dig deeper
for child in node.children.borrow().iter() {
test_walk(child, &mut *i);
}
}
NodeData::Element { ref name, .. } => {
let node_name = name.local.as_ref().to_string();
if node_name == "body" {
assert_eq!(html::get_node_attr(node, "background"), Some(str!("1")));
html::set_node_attr(node, "background", None);
assert_eq!(html::get_node_attr(node, "background"), None);
}
for child in node.children.borrow().iter() {
test_walk(child, &mut *i);
}
}
_ => (),
};
}
test_walk(&dom.document, &mut count);
assert_eq!(count, 5);
}
}

View File

@@ -87,6 +87,7 @@ mod passing {
#[test]
fn no_css() {
let html = "<link rel=\"stylesheet\" href=\"main.css\">\
<link rel=\"alternate stylesheet\" href=\"main.css\">\
<style>html{background-color: #000;}</style>\
<div style=\"display: none;\"></div>";
let dom = html::html_to_dom(&html);
@@ -109,6 +110,7 @@ mod passing {
"<html>\
<head>\
<link rel=\"stylesheet\">\
<link rel=\"alternate stylesheet\">\
<style></style>\
</head>\
<body>\
@@ -319,11 +321,52 @@ mod passing {
buf.iter().map(|&c| c as char).collect::<String>(),
"<html>\
<head>\
<meta>\
<meta>\
<meta http-equiv=\"disabled by monolith (Refresh)\" value=\"20\">\
<meta http-equiv=\"disabled by monolith (Location)\" value=\"https://freebsd.org\">\
</head>\
<body></body>\
</html>"
);
}
#[test]
fn processes_noscript_tags() {
let html = "<html>\
<body>\
<noscript>\
<img src=\"image.png\" />\
</noscript>\
</body>\
</html>";
let dom = html::html_to_dom(&html);
let url = "http://localhost";
let cache = &mut HashMap::new();
let mut options = Options::default();
options.no_images = true;
options.silent = true;
let client = Client::new();
html::walk_and_embed_assets(cache, &client, &url, &dom.document, &options, 0);
let mut buf: Vec<u8> = Vec::new();
serialize(&mut buf, &dom.document, SerializeOpts::default()).unwrap();
assert_eq!(
buf.iter().map(|&c| c as char).collect::<String>(),
format!(
"<html>\
<head>\
</head>\
<body>\
<noscript>\
<img src=\"{}\">\
</noscript>\
</body>\
</html>",
empty_image!(),
)
);
}
}

View File

@@ -4,4 +4,5 @@ mod html;
mod js;
mod macros;
mod opts;
mod url;
mod utils;

View File

@@ -13,7 +13,8 @@ mod passing {
fn defaults() {
let options: Options = Options::default();
assert_eq!(options.target, str!());
assert_eq!(options.no_audio, false);
assert_eq!(options.base_url, None);
assert_eq!(options.no_css, false);
assert_eq!(options.no_frames, false);
assert_eq!(options.no_fonts, false);
@@ -25,6 +26,9 @@ mod passing {
assert_eq!(options.output, str!());
assert_eq!(options.silent, false);
assert_eq!(options.timeout, 0);
assert_eq!(options.user_agent, "");
assert_eq!(options.user_agent, None);
assert_eq!(options.no_video, false);
assert_eq!(options.target, str!());
}
}

View File

@@ -18,9 +18,31 @@ mod passing {
"test"
);
}
}
// ███████╗ █████╗ ██╗██╗ ██╗███╗ ██╗ ██████╗
// ██╔════╝██╔══██╗██║██║ ██║████╗ ██║██╔════╝
// █████╗ ███████║██║██║ ██║██╔██╗ ██║██║ ███╗
// ██╔══╝ ██╔══██║██║██║ ██║██║╚██╗██║██║ ██║
// ██║ ██║ ██║██║███████╗██║██║ ╚████║╚██████╔╝
// ╚═╝ ╚═╝ ╚═╝╚═╝╚══════╝╚═╝╚═╝ ╚═══╝ ╚═════╝
#[cfg(test)]
mod failing {
use crate::url;
#[test]
fn https_empty() {
assert_eq!(url::get_url_fragment("https://kernel.org#"), "");
}
#[test]
fn no_fragment() {
assert_eq!(url::get_url_fragment("https://kernel.org"), "");
}
#[test]
fn dummy_data_url() {
assert_eq!(url::get_url_fragment("data:text/html,"), "");
}
}

View File

@@ -1,12 +1,12 @@
mod clean_url;
mod data_to_data_url;
mod data_url_to_data;
mod decode_url;
mod file_url_to_fs_path;
mod get_url_fragment;
mod is_data_url;
mod is_file_url;
mod is_http_url;
mod parse_data_url;
mod resolve_url;
mod url_has_protocol;
mod url_with_fragment;

View File

@@ -11,7 +11,7 @@ mod passing {
#[test]
fn parse_text_html_base64() {
let (media_type, data) = url::data_url_to_data("data:text/html;base64,V29yayBleHBhbmRzIHNvIGFzIHRvIGZpbGwgdGhlIHRpbWUgYXZhaWxhYmxlIGZvciBpdHMgY29tcGxldGlvbg==");
let (media_type, data) = url::parse_data_url("data:text/html;base64,V29yayBleHBhbmRzIHNvIGFzIHRvIGZpbGwgdGhlIHRpbWUgYXZhaWxhYmxlIGZvciBpdHMgY29tcGxldGlvbg==");
assert_eq!(media_type, "text/html");
assert_eq!(
@@ -22,7 +22,7 @@ mod passing {
#[test]
fn parse_text_html_utf8() {
let (media_type, data) = url::data_url_to_data(
let (media_type, data) = url::parse_data_url(
"data:text/html;utf8,Work expands so as to fill the time available for its completion",
);
@@ -35,7 +35,7 @@ mod passing {
#[test]
fn parse_text_html_plaintext() {
let (media_type, data) = url::data_url_to_data(
let (media_type, data) = url::parse_data_url(
"data:text/html,Work expands so as to fill the time available for its completion",
);
@@ -48,7 +48,7 @@ mod passing {
#[test]
fn parse_text_html_charset_utf_8_between_two_whitespaces() {
let (media_type, data) = url::data_url_to_data(" data:text/html;charset=utf-8,Work expands so as to fill the time available for its completion ");
let (media_type, data) = url::parse_data_url(" data:text/html;charset=utf-8,Work expands so as to fill the time available for its completion ");
assert_eq!(media_type, "text/html");
assert_eq!(
@@ -59,8 +59,7 @@ mod passing {
#[test]
fn parse_text_css_url_encoded() {
let (media_type, data) =
url::data_url_to_data("data:text/css,div{background-color:%23000}");
let (media_type, data) = url::parse_data_url("data:text/css,div{background-color:%23000}");
assert_eq!(media_type, "text/css");
assert_eq!(String::from_utf8_lossy(&data), "div{background-color:#000}");
@@ -68,7 +67,7 @@ mod passing {
#[test]
fn parse_no_media_type_base64() {
let (media_type, data) = url::data_url_to_data("data:;base64,dGVzdA==");
let (media_type, data) = url::parse_data_url("data:;base64,dGVzdA==");
assert_eq!(media_type, "");
assert_eq!(String::from_utf8_lossy(&data), "test");
@@ -76,7 +75,7 @@ mod passing {
#[test]
fn parse_no_media_type_no_encoding() {
let (media_type, data) = url::data_url_to_data("data:;,test%20test");
let (media_type, data) = url::parse_data_url("data:;,test%20test");
assert_eq!(media_type, "");
assert_eq!(String::from_utf8_lossy(&data), "test test");
@@ -96,7 +95,7 @@ mod failing {
#[test]
fn just_word_data() {
let (media_type, data) = url::data_url_to_data("data");
let (media_type, data) = url::parse_data_url("data");
assert_eq!(media_type, "");
assert_eq!(String::from_utf8_lossy(&data), "");

View File

@@ -7,208 +7,165 @@
#[cfg(test)]
mod passing {
use url::ParseError;
use crate::url;
#[test]
fn from_https_to_level_up_relative() -> Result<(), ParseError> {
let resolved_url =
url::resolve_url("https://www.kernel.org", "../category/signatures.html")?;
fn from_https_to_level_up_relative() {
assert_eq!(
resolved_url.as_str(),
url::resolve_url("https://www.kernel.org", "../category/signatures.html")
.unwrap_or_default(),
"https://www.kernel.org/category/signatures.html"
);
Ok(())
}
#[test]
fn from_just_filename_to_full_https_url() -> Result<(), ParseError> {
let resolved_url = url::resolve_url(
"saved_page.htm",
"https://www.kernel.org/category/signatures.html",
)?;
fn from_just_filename_to_full_https_url() {
assert_eq!(
resolved_url.as_str(),
url::resolve_url(
"saved_page.htm",
"https://www.kernel.org/category/signatures.html",
)
.unwrap_or_default(),
"https://www.kernel.org/category/signatures.html"
);
Ok(())
}
#[test]
fn from_https_url_to_url_with_no_protocol() -> Result<(), ParseError> {
let resolved_url = url::resolve_url(
"https://www.kernel.org",
"//www.kernel.org/theme/images/logos/tux.png",
)?;
fn from_https_url_to_url_with_no_protocol() {
assert_eq!(
resolved_url.as_str(),
url::resolve_url(
"https://www.kernel.org",
"//www.kernel.org/theme/images/logos/tux.png",
)
.unwrap_or_default(),
"https://www.kernel.org/theme/images/logos/tux.png"
);
Ok(())
}
#[test]
fn from_https_url_to_url_with_no_protocol_and_on_different_hostname() -> Result<(), ParseError>
{
let resolved_url = url::resolve_url(
"https://www.kernel.org",
"//another-host.org/theme/images/logos/tux.png",
)?;
fn from_https_url_to_url_with_no_protocol_and_on_different_hostname() {
assert_eq!(
resolved_url.as_str(),
url::resolve_url(
"https://www.kernel.org",
"//another-host.org/theme/images/logos/tux.png",
)
.unwrap_or_default(),
"https://another-host.org/theme/images/logos/tux.png"
);
Ok(())
}
#[test]
fn from_https_url_to_relative_root_path() -> Result<(), ParseError> {
let resolved_url = url::resolve_url(
"https://www.kernel.org/category/signatures.html",
"/theme/images/logos/tux.png",
)?;
fn from_https_url_to_relative_root_path() {
assert_eq!(
resolved_url.as_str(),
url::resolve_url(
"https://www.kernel.org/category/signatures.html",
"/theme/images/logos/tux.png",
)
.unwrap_or_default(),
"https://www.kernel.org/theme/images/logos/tux.png"
);
Ok(())
}
#[test]
fn from_https_to_just_filename() -> Result<(), ParseError> {
let resolved_url = url::resolve_url(
"https://www.w3schools.com/html/html_iframe.asp",
"default.asp",
)?;
fn from_https_to_just_filename() {
assert_eq!(
resolved_url.as_str(),
url::resolve_url(
"https://www.w3schools.com/html/html_iframe.asp",
"default.asp",
)
.unwrap_or_default(),
"https://www.w3schools.com/html/default.asp"
);
Ok(())
}
#[test]
fn from_data_url_to_https() -> Result<(), ParseError> {
let resolved_url = url::resolve_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h",
"https://www.kernel.org/category/signatures.html",
)?;
fn from_data_url_to_https() {
assert_eq!(
resolved_url.as_str(),
url::resolve_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h",
"https://www.kernel.org/category/signatures.html",
)
.unwrap_or_default(),
"https://www.kernel.org/category/signatures.html"
);
Ok(())
}
#[test]
fn from_data_url_to_data_url() -> Result<(), ParseError> {
let resolved_url = url::resolve_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h",
"data:text/html;base64,PGEgaHJlZj0iaW5kZXguaHRtbCI+SG9tZTwvYT4K",
)?;
fn from_data_url_to_data_url() {
assert_eq!(
resolved_url.as_str(),
url::resolve_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h",
"data:text/html;base64,PGEgaHJlZj0iaW5kZXguaHRtbCI+SG9tZTwvYT4K",
)
.unwrap_or_default(),
"data:text/html;base64,PGEgaHJlZj0iaW5kZXguaHRtbCI+SG9tZTwvYT4K"
);
Ok(())
}
#[test]
fn from_file_url_to_relative_path() -> Result<(), ParseError> {
let resolved_url = url::resolve_url(
"file:///home/user/Websites/my-website/index.html",
"assets/images/logo.png",
)
.unwrap_or(str!());
fn from_file_url_to_relative_path() {
assert_eq!(
resolved_url.as_str(),
url::resolve_url(
"file:///home/user/Websites/my-website/index.html",
"assets/images/logo.png",
)
.unwrap_or_default(),
"file:///home/user/Websites/my-website/assets/images/logo.png"
);
Ok(())
}
#[test]
fn from_file_url_to_relative_path_with_backslashes() -> Result<(), ParseError> {
let resolved_url = url::resolve_url(
"file:\\\\\\home\\user\\Websites\\my-website\\index.html",
"assets\\images\\logo.png",
)
.unwrap_or(str!());
fn from_file_url_to_relative_path_with_backslashes() {
assert_eq!(
resolved_url.as_str(),
url::resolve_url(
"file:\\\\\\home\\user\\Websites\\my-website\\index.html",
"assets\\images\\logo.png",
)
.unwrap_or_default(),
"file:///home/user/Websites/my-website/assets/images/logo.png"
);
Ok(())
}
#[test]
fn from_data_url_to_file_url() -> Result<(), ParseError> {
let resolved_url = url::resolve_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h",
"file:///etc/passwd",
)
.unwrap_or(str!());
assert_eq!(resolved_url.as_str(), "file:///etc/passwd");
Ok(())
}
#[test]
fn preserve_fragment() -> Result<(), ParseError> {
let resolved_url = url::resolve_url(
"http://doesnt-matter.local/",
"css/fonts/fontmarvelous.svg#fontmarvelous",
)
.unwrap_or(str!());
fn from_data_url_to_file_url() {
assert_eq!(
resolved_url.as_str(),
url::resolve_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h",
"file:///etc/passwd",
)
.unwrap_or_default(),
"file:///etc/passwd"
);
}
#[test]
fn preserve_fragment() {
assert_eq!(
url::resolve_url(
"http://doesnt-matter.local/",
"css/fonts/fontmarvelous.svg#fontmarvelous",
)
.unwrap_or_default(),
"http://doesnt-matter.local/css/fonts/fontmarvelous.svg#fontmarvelous"
);
Ok(())
}
#[test]
fn resolve_from_file_url_to_file_url() -> Result<(), ParseError> {
let resolved_url = if cfg!(windows) {
url::resolve_url("file:///c:/index.html", "file:///c:/image.png").unwrap_or(str!())
} else {
url::resolve_url("file:///tmp/index.html", "file:///tmp/image.png").unwrap_or(str!())
};
fn resolve_from_file_url_to_file_url() {
assert_eq!(
resolved_url.as_str(),
if cfg!(windows) {
url::resolve_url("file:///c:/index.html", "file:///c:/image.png")
.unwrap_or_default()
} else {
url::resolve_url("file:///tmp/index.html", "file:///tmp/image.png")
.unwrap_or_default()
},
if cfg!(windows) {
"file:///c:/image.png"
} else {
"file:///tmp/image.png"
}
);
Ok(())
}
}
@@ -222,18 +179,16 @@ mod passing {
#[cfg(test)]
mod failing {
use crate::url;
use url::ParseError;
#[test]
fn from_data_url_to_url_with_no_protocol() -> Result<(), ParseError> {
let resolved_url = url::resolve_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h",
"//www.w3schools.com/html/html_iframe.asp",
)
.unwrap_or(str!());
assert_eq!(resolved_url.as_str(), "");
Ok(())
fn from_data_url_to_url_with_no_protocol() {
assert_eq!(
url::resolve_url(
"data:text/html;base64,V2VsY29tZSBUbyBUaGUgUGFydHksIDxiPlBhbDwvYj4h",
"//www.w3schools.com/html/html_iframe.asp",
)
.unwrap_or_default(),
""
);
}
}

View File

@@ -54,6 +54,11 @@ mod passing {
"MAILTO:somebody@somewhere.com?subject=hello"
));
}
#[test]
fn empty_data_url() {
assert!(url::url_has_protocol("data:text/html,"));
}
}
// ███████╗ █████╗ ██╗██╗ ██╗███╗ ██╗ ██████╗
@@ -65,13 +70,11 @@ mod passing {
#[cfg(test)]
mod failing {
use crate::utils;
use crate::url;
#[test]
fn url_with_no_protocol() {
assert!(!url::url_has_protocol(
"//some-hostname.com/some-file.html"
));
assert!(!url::url_has_protocol("//some-hostname.com/some-file.html"));
}
#[test]

View File

@@ -11,6 +11,7 @@ mod passing {
use std::collections::HashMap;
use std::env;
use crate::opts::Options;
use crate::url;
use crate::utils;
@@ -19,6 +20,9 @@ mod passing {
let cache = &mut HashMap::new();
let client = Client::new();
let mut options = Options::default();
options.silent = true;
// If both source and target are data URLs,
// ensure the result contains target data URL
let (data, final_url, media_type) = utils::retrieve_asset(
@@ -26,7 +30,7 @@ mod passing {
&client,
"data:text/html;base64,c291cmNl",
"data:text/html;base64,dGFyZ2V0",
false,
&options,
0,
)
.unwrap();
@@ -46,6 +50,9 @@ mod passing {
let cache = &mut HashMap::new();
let client = Client::new();
let mut options = Options::default();
options.silent = true;
let file_url_protocol: &str = if cfg!(windows) { "file:///" } else { "file://" };
// Inclusion of local assets from local sources should be allowed
@@ -63,7 +70,7 @@ mod passing {
file = file_url_protocol,
cwd = cwd.to_str().unwrap()
),
false,
&options,
0,
)
.unwrap();
@@ -91,6 +98,7 @@ mod failing {
use reqwest::blocking::Client;
use std::collections::HashMap;
use crate::opts::Options;
use crate::utils;
#[test]
@@ -98,13 +106,16 @@ mod failing {
let cache = &mut HashMap::new();
let client = Client::new();
let mut options = Options::default();
options.silent = true;
// Inclusion of local assets from data URL sources should not be allowed
match utils::retrieve_asset(
cache,
&client,
"data:text/html;base64,SoUrCe",
"file:///etc/passwd",
false,
&options,
0,
) {
Ok((..)) => {
@@ -121,13 +132,16 @@ mod failing {
let cache = &mut HashMap::new();
let client = Client::new();
let mut options = Options::default();
options.silent = true;
// Inclusion of local assets from remote sources should not be allowed
match utils::retrieve_asset(
cache,
&client,
"https://kernel.org/",
"file:///etc/passwd",
false,
&options,
0,
) {
Ok((..)) => {

View File

@@ -33,45 +33,6 @@ pub fn data_to_data_url(media_type: &str, data: &[u8], url: &str) -> String {
format!("data:{};base64,{}", media_type, base64::encode(data))
}
pub fn data_url_to_data<T: AsRef<str>>(url: T) -> (String, Vec<u8>) {
let parsed_url: Url = Url::parse(url.as_ref()).unwrap_or(Url::parse("data:,").unwrap());
let path: String = parsed_url.path().to_string();
let comma_loc: usize = path.find(',').unwrap_or(path.len());
let meta_data: String = path.chars().take(comma_loc).collect();
let raw_data: String = path.chars().skip(comma_loc + 1).collect();
let text: String = decode_url(raw_data);
let meta_data_items: Vec<&str> = meta_data.split(';').collect();
let mut media_type: String = str!();
let mut encoding: &str = "";
let mut i: i8 = 0;
for item in &meta_data_items {
if i == 0 {
media_type = str!(item);
} else {
if item.eq_ignore_ascii_case("base64")
|| item.eq_ignore_ascii_case("utf8")
|| item.eq_ignore_ascii_case("charset=UTF-8")
{
encoding = item;
}
}
i = i + 1;
}
let data: Vec<u8> = if encoding.eq_ignore_ascii_case("base64") {
base64::decode(&text).unwrap_or(vec![])
} else {
text.as_bytes().to_vec()
};
(media_type, data)
}
pub fn decode_url(input: String) -> String {
let input: String = input.replace("+", "%2B");
@@ -113,10 +74,9 @@ pub fn file_url_to_fs_path(url: &str) -> String {
}
pub fn get_url_fragment<T: AsRef<str>>(url: T) -> String {
if Url::parse(url.as_ref()).unwrap().fragment() == None {
str!()
} else {
str!(Url::parse(url.as_ref()).unwrap().fragment().unwrap())
match Url::parse(url.as_ref()) {
Ok(parsed_url) => parsed_url.fragment().unwrap_or("").to_string(),
Err(_err) => str!(),
}
}
@@ -138,6 +98,45 @@ pub fn is_http_url<T: AsRef<str>>(url: T) -> bool {
.unwrap_or(false)
}
pub fn parse_data_url<T: AsRef<str>>(url: T) -> (String, Vec<u8>) {
let parsed_url: Url = Url::parse(url.as_ref()).unwrap_or(Url::parse("data:,").unwrap());
let path: String = parsed_url.path().to_string();
let comma_loc: usize = path.find(',').unwrap_or(path.len());
let meta_data: String = path.chars().take(comma_loc).collect();
let raw_data: String = path.chars().skip(comma_loc + 1).collect();
let text: String = decode_url(raw_data);
let meta_data_items: Vec<&str> = meta_data.split(';').collect();
let mut media_type: String = str!();
let mut encoding: &str = "";
let mut i: i8 = 0;
for item in &meta_data_items {
if i == 0 {
media_type = str!(item);
} else {
if item.eq_ignore_ascii_case("base64")
|| item.eq_ignore_ascii_case("utf8")
|| item.eq_ignore_ascii_case("charset=UTF-8")
{
encoding = item;
}
}
i = i + 1;
}
let data: Vec<u8> = if encoding.eq_ignore_ascii_case("base64") {
base64::decode(&text).unwrap_or(vec![])
} else {
text.as_bytes().to_vec()
};
(media_type, data)
}
pub fn resolve_url<T: AsRef<str>, U: AsRef<str>>(from: T, to: U) -> Result<String, ParseError> {
let result = if is_http_url(to.as_ref()) {
to.as_ref().to_string()

View File

@@ -4,9 +4,12 @@ use std::collections::HashMap;
use std::fs;
use std::path::Path;
use crate::url::{clean_url, data_url_to_data, file_url_to_fs_path, is_data_url, is_file_url};
use crate::opts::Options;
use crate::url::{clean_url, file_url_to_fs_path, is_data_url, is_file_url, parse_data_url};
const INDENT: &str = " ";
const ANSI_COLOR_RED: &'static str = "\x1b[31m";
const ANSI_COLOR_RESET: &'static str = "\x1b[0m";
const INDENT: &'static str = " ";
const MAGIC: [[&[u8]; 2]; 18] = [
// Image
@@ -31,13 +34,14 @@ const MAGIC: [[&[u8]; 2]; 18] = [
[b"....moov", b"video/quicktime"],
[b"\x1A\x45\xDF\xA3", b"video/webm"],
];
const PLAINTEXT_MEDIA_TYPES: &[&str] = &[
"application/javascript",
"image/svg+xml",
"text/css",
"text/html",
"text/javascript",
"text/plain",
// "text/css",
// "text/csv",
// "text/html",
// "text/javascript",
// "text/plain",
];
pub fn detect_media_type(data: &[u8], url: &str) -> String {
@@ -55,7 +59,8 @@ pub fn detect_media_type(data: &[u8], url: &str) -> String {
}
pub fn is_plaintext_media_type(media_type: &str) -> bool {
PLAINTEXT_MEDIA_TYPES.contains(&media_type.to_lowercase().as_str())
media_type.to_lowercase().as_str().starts_with("text/")
|| PLAINTEXT_MEDIA_TYPES.contains(&media_type.to_lowercase().as_str())
}
pub fn indent(level: u32) -> String {
@@ -73,7 +78,7 @@ pub fn retrieve_asset(
client: &Client,
parent_url: &str,
url: &str,
opt_silent: bool,
options: &Options,
depth: u32,
) -> Result<(Vec<u8>, String, String), reqwest::Error> {
if url.len() == 0 {
@@ -82,7 +87,7 @@ pub fn retrieve_asset(
}
if is_data_url(&url) {
let (media_type, data) = data_url_to_data(url);
let (media_type, data) = parse_data_url(url);
Ok((data, url.to_string(), media_type))
} else if is_file_url(&url) {
// Check if parent_url is also file:///
@@ -95,7 +100,7 @@ pub fn retrieve_asset(
let fs_file_path: String = file_url_to_fs_path(url);
let path = Path::new(&fs_file_path);
if path.exists() {
if !opt_silent {
if !options.silent {
eprintln!("{}{}", indent(depth).as_str(), &url);
}
@@ -109,7 +114,7 @@ pub fn retrieve_asset(
if cache.contains_key(&cache_key) {
// URL is in cache, we get and return it
if !opt_silent {
if !options.silent {
eprintln!("{}{} (from cache)", indent(depth).as_str(), &url);
}
@@ -120,34 +125,57 @@ pub fn retrieve_asset(
))
} else {
// URL not in cache, we retrieve the file
let mut response = client.get(url).send()?;
let res_url = response.url().to_string();
match client.get(url).send() {
Ok(mut response) => {
if !options.ignore_errors && response.status() != 200 {
if !options.silent {
eprintln!(
"{}{}{} ({}){}",
indent(depth).as_str(),
if options.no_color { "" } else { ANSI_COLOR_RED },
&url,
response.status(),
if options.no_color {
""
} else {
ANSI_COLOR_RESET
},
);
}
// Provoke error
return Err(client.get("").send().unwrap_err());
}
if !opt_silent {
if url == res_url {
eprintln!("{}{}", indent(depth).as_str(), &url);
} else {
eprintln!("{}{} -> {}", indent(depth).as_str(), &url, &res_url);
let res_url = response.url().to_string();
if !options.silent {
if url == res_url {
eprintln!("{}{}", indent(depth).as_str(), &url);
} else {
eprintln!("{}{} -> {}", indent(depth).as_str(), &url, &res_url);
}
}
let new_cache_key: String = clean_url(&res_url);
// Convert response into a byte array
let mut data: Vec<u8> = vec![];
response.copy_to(&mut data)?;
// Attempt to obtain media type by reading the Content-Type header
let media_type = response
.headers()
.get(CONTENT_TYPE)
.and_then(|header| header.to_str().ok())
.unwrap_or("");
// Add retrieved resource to cache
cache.insert(new_cache_key, data.clone());
Ok((data, res_url, media_type.to_string()))
}
Err(error) => Err(error),
}
let new_cache_key: String = clean_url(&res_url);
// Convert response into a byte array
let mut data: Vec<u8> = vec![];
response.copy_to(&mut data)?;
// Attempt to obtain media type by reading the Content-Type header
let media_type = response
.headers()
.get(CONTENT_TYPE)
.and_then(|header| header.to_str().ok())
.unwrap_or("");
// Add to cache
cache.insert(new_cache_key, data.clone());
Ok((data, res_url, media_type.to_string()))
}
}
}

10
utils/run-in-container.sh Normal file
View File

@@ -0,0 +1,10 @@
#!/bin/sh
DOCKER=docker
PROG_NAME=monolith
if which podman 2>&1 > /dev/null; then
DOCKER=podman
fi
$DOCKER run --rm Y2Z/$PROG_NAME $PROG_NAME "$@"