feat(tazjin/tgsa): Implement initial tg embed -> BBcode features

Supports only posts with plain photos, and loses all message
formatting, but it's getting there.

Change-Id: I9e4afcf3072d1e0724521ccbdc1338fe4f8d5ebe
Reviewed-on: https://cl.tvl.fyi/c/depot/+/5466
Tested-by: BuildkiteCI
Reviewed-by: tazjin <tazjin@tvl.su>
This commit is contained in:
Vincent Ambo 2022-04-16 21:04:02 +02:00 committed by tazjin
parent 632c4280b5
commit 3d58dfb4ab
5 changed files with 1082 additions and 0 deletions

3
users/tazjin/tgsa/.gitignore vendored Normal file
View file

@ -0,0 +1,3 @@
result
/target
**/*.rs.bk

919
users/tazjin/tgsa/Cargo.lock generated Normal file
View file

@ -0,0 +1,919 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 3
[[package]]
name = "anyhow"
version = "1.0.56"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4361135be9122e0870de935d7c439aef945b9f9ddd4199a553b5270b49c82a27"
[[package]]
name = "autocfg"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
[[package]]
name = "bitflags"
version = "1.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
[[package]]
name = "byteorder"
version = "1.4.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"
[[package]]
name = "cc"
version = "1.0.73"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2fff2a6927b3bb87f9595d67196a70493f627687a71d87a0d692242c33f58c11"
[[package]]
name = "cfg-if"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
[[package]]
name = "convert_case"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6245d59a3e82a7fc217c5828a6692dbc6dfb63a0c8c90495621f7b9d79704a0e"
[[package]]
name = "crimp"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bbe8f9a320ad9c1a2e3bacedaa281587bd297fb10a10179fd39f777049d04794"
dependencies = [
"curl",
"serde",
"serde_json",
]
[[package]]
name = "cssparser"
version = "0.27.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "754b69d351cdc2d8ee09ae203db831e005560fc6030da058f86ad60c92a9cb0a"
dependencies = [
"cssparser-macros",
"dtoa-short",
"itoa 0.4.8",
"matches",
"phf",
"proc-macro2",
"quote",
"smallvec",
"syn",
]
[[package]]
name = "cssparser-macros"
version = "0.6.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dfae75de57f2b2e85e8768c3ea840fd159c8f33e2b6522c7835b7abac81be16e"
dependencies = [
"quote",
"syn",
]
[[package]]
name = "curl"
version = "0.4.43"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "37d855aeef205b43f65a5001e0997d81f8efca7badad4fad7d897aa7f0d0651f"
dependencies = [
"curl-sys",
"libc",
"openssl-probe",
"openssl-sys",
"schannel",
"socket2",
"winapi",
]
[[package]]
name = "curl-sys"
version = "0.4.53+curl-7.82.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8092905a5a9502c312f223b2775f57ec5c5b715f9a15ee9d2a8591d1364a0352"
dependencies = [
"cc",
"libc",
"libz-sys",
"openssl-sys",
"pkg-config",
"vcpkg",
"winapi",
]
[[package]]
name = "derive_more"
version = "0.99.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4fb810d30a7c1953f91334de7244731fc3f3c10d7fe163338a35b9f640960321"
dependencies = [
"convert_case",
"proc-macro2",
"quote",
"rustc_version",
"syn",
]
[[package]]
name = "dtoa"
version = "0.4.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "56899898ce76aaf4a0f24d914c97ea6ed976d42fec6ad33fcbb0a1103e07b2b0"
[[package]]
name = "dtoa-short"
version = "0.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bde03329ae10e79ede66c9ce4dc930aa8599043b0743008548680f25b91502d6"
dependencies = [
"dtoa",
]
[[package]]
name = "ego-tree"
version = "0.6.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3a68a4904193147e0a8dec3314640e6db742afd5f6e634f428a6af230d9b3591"
[[package]]
name = "form_urlencoded"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5fc25a87fa4fd2094bffb06925852034d90a17f0d1e05197d4956d3555752191"
dependencies = [
"matches",
"percent-encoding",
]
[[package]]
name = "futf"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "df420e2e84819663797d1ec6544b13c5be84629e7bb00dc960d6917db2987843"
dependencies = [
"mac",
"new_debug_unreachable",
]
[[package]]
name = "fxhash"
version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c31b6d751ae2c7f11320402d34e41349dd1016f8d5d45e48c4312bc8625af50c"
dependencies = [
"byteorder",
]
[[package]]
name = "getopts"
version = "0.2.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "14dbbfd5c71d70241ecf9e6f13737f7b5ce823821063188d7e46c41d371eebd5"
dependencies = [
"unicode-width",
]
[[package]]
name = "getrandom"
version = "0.1.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8fc3cb4d91f53b50155bdcfd23f6a4c39ae1969c2ae85982b135750cccaf5fce"
dependencies = [
"cfg-if",
"libc",
"wasi 0.9.0+wasi-snapshot-preview1",
]
[[package]]
name = "getrandom"
version = "0.2.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9be70c98951c83b8d2f8f60d7065fa6d5146873094452a1008da8c2f1e4205ad"
dependencies = [
"cfg-if",
"libc",
"wasi 0.10.2+wasi-snapshot-preview1",
]
[[package]]
name = "html5ever"
version = "0.25.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e5c13fb08e5d4dfc151ee5e88bae63f7773d61852f3bdc73c9f4b9e1bde03148"
dependencies = [
"log",
"mac",
"markup5ever",
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "idna"
version = "0.2.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "418a0a6fab821475f634efe3ccc45c013f742efe03d853e8d3355d5cb850ecf8"
dependencies = [
"matches",
"unicode-bidi",
"unicode-normalization",
]
[[package]]
name = "itoa"
version = "0.4.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b71991ff56294aa922b450139ee08b3bfc70982c6b2c7562771375cf73542dd4"
[[package]]
name = "itoa"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1aab8fc367588b89dcee83ab0fd66b72b50b72fa1904d7095045ace2b0c81c35"
[[package]]
name = "lazy_static"
version = "1.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
[[package]]
name = "libc"
version = "0.2.123"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cb691a747a7ab48abc15c5b42066eaafde10dc427e3b6ee2a1cf43db04c763bd"
[[package]]
name = "libz-sys"
version = "1.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6f35facd4a5673cb5a48822be2be1d4236c1c99cb4113cab7061ac720d5bf859"
dependencies = [
"cc",
"libc",
"pkg-config",
"vcpkg",
]
[[package]]
name = "lock_api"
version = "0.4.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "327fa5b6a6940e4699ec49a9beae1ea4845c6bab9314e4f84ac68742139d8c53"
dependencies = [
"autocfg",
"scopeguard",
]
[[package]]
name = "log"
version = "0.4.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6389c490849ff5bc16be905ae24bc913a9c8892e19b2341dbc175e14c341c2b8"
dependencies = [
"cfg-if",
]
[[package]]
name = "mac"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4"
[[package]]
name = "markup5ever"
version = "0.10.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a24f40fb03852d1cdd84330cddcaf98e9ec08a7b7768e952fad3b4cf048ec8fd"
dependencies = [
"log",
"phf",
"phf_codegen",
"string_cache",
"string_cache_codegen",
"tendril",
]
[[package]]
name = "matches"
version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a3e378b66a060d48947b590737b30a1be76706c8dd7b8ba0f2fe3989c68a853f"
[[package]]
name = "new_debug_unreachable"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e4a24736216ec316047a1fc4252e27dabb04218aa4a3f37c6e7ddbf1f9782b54"
[[package]]
name = "nodrop"
version = "0.1.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "72ef4a56884ca558e5ddb05a1d1e7e1bfd9a68d9ed024c21704cc98872dae1bb"
[[package]]
name = "once_cell"
version = "1.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "87f3e037eac156d1775da914196f0f37741a274155e34a0b7e427c35d2a2ecb9"
[[package]]
name = "openssl-probe"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ff011a302c396a5197692431fc1948019154afc178baf7d8e37367442a4601cf"
[[package]]
name = "openssl-sys"
version = "0.9.72"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7e46109c383602735fa0a2e48dd2b7c892b048e1bf69e5c3b1d804b7d9c203cb"
dependencies = [
"autocfg",
"cc",
"libc",
"pkg-config",
"vcpkg",
]
[[package]]
name = "parking_lot"
version = "0.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "87f5ec2493a61ac0506c0f4199f99070cbe83857b0337006a30f3e6719b8ef58"
dependencies = [
"lock_api",
"parking_lot_core",
]
[[package]]
name = "parking_lot_core"
version = "0.9.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "995f667a6c822200b0433ac218e05582f0e2efa1b922a3fd2fbaadc5f87bab37"
dependencies = [
"cfg-if",
"libc",
"redox_syscall",
"smallvec",
"windows-sys",
]
[[package]]
name = "percent-encoding"
version = "2.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d4fd5641d01c8f18a23da7b6fe29298ff4b55afcccdf78973b24cf3175fee32e"
[[package]]
name = "phf"
version = "0.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3dfb61232e34fcb633f43d12c58f83c1df82962dcdfa565a4e866ffc17dafe12"
dependencies = [
"phf_macros",
"phf_shared 0.8.0",
"proc-macro-hack",
]
[[package]]
name = "phf_codegen"
version = "0.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cbffee61585b0411840d3ece935cce9cb6321f01c45477d30066498cd5e1a815"
dependencies = [
"phf_generator 0.8.0",
"phf_shared 0.8.0",
]
[[package]]
name = "phf_generator"
version = "0.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "17367f0cc86f2d25802b2c26ee58a7b23faeccf78a396094c13dced0d0182526"
dependencies = [
"phf_shared 0.8.0",
"rand 0.7.3",
]
[[package]]
name = "phf_generator"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5d5285893bb5eb82e6aaf5d59ee909a06a16737a8970984dd7746ba9283498d6"
dependencies = [
"phf_shared 0.10.0",
"rand 0.8.5",
]
[[package]]
name = "phf_macros"
version = "0.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7f6fde18ff429ffc8fe78e2bf7f8b7a5a5a6e2a8b58bc5a9ac69198bbda9189c"
dependencies = [
"phf_generator 0.8.0",
"phf_shared 0.8.0",
"proc-macro-hack",
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "phf_shared"
version = "0.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c00cf8b9eafe68dde5e9eaa2cef8ee84a9336a47d566ec55ca16589633b65af7"
dependencies = [
"siphasher",
]
[[package]]
name = "phf_shared"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6796ad771acdc0123d2a88dc428b5e38ef24456743ddb1744ed628f9815c096"
dependencies = [
"siphasher",
]
[[package]]
name = "pkg-config"
version = "0.3.25"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1df8c4ec4b0627e53bdf214615ad287367e482558cf84b109250b37464dc03ae"
[[package]]
name = "ppv-lite86"
version = "0.2.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "eb9f9e6e233e5c4a35559a617bf40a4ec447db2e84c20b55a6f83167b7e57872"
[[package]]
name = "precomputed-hash"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "925383efa346730478fb4838dbe9137d2a47675ad789c546d150a6e1dd4ab31c"
[[package]]
name = "proc-macro-hack"
version = "0.5.19"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dbf0c48bc1d91375ae5c3cd81e3722dff1abcf81a30960240640d223f59fe0e5"
[[package]]
name = "proc-macro2"
version = "1.0.37"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ec757218438d5fda206afc041538b2f6d889286160d649a86a24d37e1235afd1"
dependencies = [
"unicode-xid",
]
[[package]]
name = "quote"
version = "1.0.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a1feb54ed693b93a84e14094943b84b7c4eae204c512b7ccb95ab0c66d278ad1"
dependencies = [
"proc-macro2",
]
[[package]]
name = "rand"
version = "0.7.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6a6b1679d49b24bbfe0c803429aa1874472f50d9b363131f0e89fc356b544d03"
dependencies = [
"getrandom 0.1.16",
"libc",
"rand_chacha 0.2.2",
"rand_core 0.5.1",
"rand_hc",
"rand_pcg",
]
[[package]]
name = "rand"
version = "0.8.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
dependencies = [
"libc",
"rand_chacha 0.3.1",
"rand_core 0.6.3",
]
[[package]]
name = "rand_chacha"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f4c8ed856279c9737206bf725bf36935d8666ead7aa69b52be55af369d193402"
dependencies = [
"ppv-lite86",
"rand_core 0.5.1",
]
[[package]]
name = "rand_chacha"
version = "0.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88"
dependencies = [
"ppv-lite86",
"rand_core 0.6.3",
]
[[package]]
name = "rand_core"
version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "90bde5296fc891b0cef12a6d03ddccc162ce7b2aff54160af9338f8d40df6d19"
dependencies = [
"getrandom 0.1.16",
]
[[package]]
name = "rand_core"
version = "0.6.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d34f1408f55294453790c48b2f1ebbb1c5b4b7563eb1f418bcfcfdbb06ebb4e7"
dependencies = [
"getrandom 0.2.6",
]
[[package]]
name = "rand_hc"
version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ca3129af7b92a17112d59ad498c6f81eaf463253766b90396d39ea7a39d6613c"
dependencies = [
"rand_core 0.5.1",
]
[[package]]
name = "rand_pcg"
version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "16abd0c1b639e9eb4d7c50c0b8100b0d0f849be2349829c740fe8e6eb4816429"
dependencies = [
"rand_core 0.5.1",
]
[[package]]
name = "redox_syscall"
version = "0.2.13"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "62f25bc4c7e55e0b0b7a1d43fb893f4fa1361d0abe38b9ce4f323c2adfe6ef42"
dependencies = [
"bitflags",
]
[[package]]
name = "rustc_version"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bfa0f585226d2e68097d4f95d113b15b83a82e819ab25717ec0590d9584ef366"
dependencies = [
"semver",
]
[[package]]
name = "ryu"
version = "1.0.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "73b4b750c782965c211b42f022f59af1fbceabdd026623714f104152f1ec149f"
[[package]]
name = "schannel"
version = "0.1.19"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8f05ba609c234e60bee0d547fe94a4c7e9da733d1c962cf6e59efa4cd9c8bc75"
dependencies = [
"lazy_static",
"winapi",
]
[[package]]
name = "scopeguard"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd"
[[package]]
name = "scraper"
version = "0.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "48e02aa790c80c2e494130dec6a522033b6a23603ffc06360e9fe6c611ea2c12"
dependencies = [
"cssparser",
"ego-tree",
"getopts",
"html5ever",
"matches",
"selectors",
"smallvec",
"tendril",
]
[[package]]
name = "selectors"
version = "0.22.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "df320f1889ac4ba6bc0cdc9c9af7af4bd64bb927bccdf32d81140dc1f9be12fe"
dependencies = [
"bitflags",
"cssparser",
"derive_more",
"fxhash",
"log",
"matches",
"phf",
"phf_codegen",
"precomputed-hash",
"servo_arc",
"smallvec",
"thin-slice",
]
[[package]]
name = "semver"
version = "1.0.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d65bd28f48be7196d222d95b9243287f48d27aca604e08497513019ff0502cc4"
[[package]]
name = "serde"
version = "1.0.136"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ce31e24b01e1e524df96f1c2fdd054405f8d7376249a5110886fb4b658484789"
[[package]]
name = "serde_json"
version = "1.0.79"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8e8d9fa5c3b304765ce1fd9c4c8a3de2c8db365a5b91be52f186efc675681d95"
dependencies = [
"itoa 1.0.1",
"ryu",
"serde",
]
[[package]]
name = "servo_arc"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d98238b800e0d1576d8b6e3de32827c2d74bee68bb97748dcf5071fb53965432"
dependencies = [
"nodrop",
"stable_deref_trait",
]
[[package]]
name = "siphasher"
version = "0.3.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7bd3e3206899af3f8b12af284fafc038cc1dc2b41d1b89dd17297221c5d225de"
[[package]]
name = "smallvec"
version = "1.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f2dd574626839106c320a323308629dcb1acfc96e32a8cba364ddc61ac23ee83"
[[package]]
name = "socket2"
version = "0.4.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "66d72b759436ae32898a2af0a14218dbf55efde3feeb170eb623637db85ee1e0"
dependencies = [
"libc",
"winapi",
]
[[package]]
name = "stable_deref_trait"
version = "1.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a8f112729512f8e442d81f95a8a7ddf2b7c6b8a1a6f509a95864142b30cab2d3"
[[package]]
name = "string_cache"
version = "0.8.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "213494b7a2b503146286049378ce02b482200519accc31872ee8be91fa820a08"
dependencies = [
"new_debug_unreachable",
"once_cell",
"parking_lot",
"phf_shared 0.10.0",
"precomputed-hash",
"serde",
]
[[package]]
name = "string_cache_codegen"
version = "0.5.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6bb30289b722be4ff74a408c3cc27edeaad656e06cb1fe8fa9231fa59c728988"
dependencies = [
"phf_generator 0.10.0",
"phf_shared 0.10.0",
"proc-macro2",
"quote",
]
[[package]]
name = "syn"
version = "1.0.91"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b683b2b825c8eef438b77c36a06dc262294da3d5a5813fac20da149241dcd44d"
dependencies = [
"proc-macro2",
"quote",
"unicode-xid",
]
[[package]]
name = "tendril"
version = "0.4.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d24a120c5fc464a3458240ee02c299ebcb9d67b5249c8848b09d639dca8d7bb0"
dependencies = [
"futf",
"mac",
"utf-8",
]
[[package]]
name = "tgsa"
version = "0.1.0"
dependencies = [
"anyhow",
"crimp",
"scraper",
"url",
]
[[package]]
name = "thin-slice"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8eaa81235c7058867fa8c0e7314f33dcce9c215f535d1913822a2b3f5e289f3c"
[[package]]
name = "tinyvec"
version = "1.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2c1c1d5a42b6245520c249549ec267180beaffcc0615401ac8e31853d4b6d8d2"
dependencies = [
"tinyvec_macros",
]
[[package]]
name = "tinyvec_macros"
version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cda74da7e1a664f795bb1f8a87ec406fb89a02522cf6e50620d016add6dbbf5c"
[[package]]
name = "unicode-bidi"
version = "0.3.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1a01404663e3db436ed2746d9fefef640d868edae3cceb81c3b8d5732fda678f"
[[package]]
name = "unicode-normalization"
version = "0.1.19"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d54590932941a9e9266f0832deed84ebe1bf2e4c9e4a3554d393d18f5e854bf9"
dependencies = [
"tinyvec",
]
[[package]]
name = "unicode-width"
version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3ed742d4ea2bd1176e236172c8429aaf54486e7ac098db29ffe6529e0ce50973"
[[package]]
name = "unicode-xid"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8ccb82d61f80a663efe1f787a51b16b5a51e3314d6ac365b08639f52387b33f3"
[[package]]
name = "url"
version = "2.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a507c383b2d33b5fc35d1861e77e6b383d158b2da5e14fe51b83dfedf6fd578c"
dependencies = [
"form_urlencoded",
"idna",
"matches",
"percent-encoding",
]
[[package]]
name = "utf-8"
version = "0.7.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "09cc8ee72d2a9becf2f2febe0205bbed8fc6615b7cb429ad062dc7b7ddd036a9"
[[package]]
name = "vcpkg"
version = "0.2.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"
[[package]]
name = "wasi"
version = "0.9.0+wasi-snapshot-preview1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cccddf32554fecc6acb585f82a32a72e28b48f8c4c1883ddfeeeaa96f7d8e519"
[[package]]
name = "wasi"
version = "0.10.2+wasi-snapshot-preview1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fd6fbd9a79829dd1ad0cc20627bf1ed606756a7f77edff7b66b7064f9cb327c6"
[[package]]
name = "winapi"
version = "0.3.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
dependencies = [
"winapi-i686-pc-windows-gnu",
"winapi-x86_64-pc-windows-gnu",
]
[[package]]
name = "winapi-i686-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
[[package]]
name = "winapi-x86_64-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
[[package]]
name = "windows-sys"
version = "0.34.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5acdd78cb4ba54c0045ac14f62d8f94a03d10047904ae2a40afa1e99d8f70825"
dependencies = [
"windows_aarch64_msvc",
"windows_i686_gnu",
"windows_i686_msvc",
"windows_x86_64_gnu",
"windows_x86_64_msvc",
]
[[package]]
name = "windows_aarch64_msvc"
version = "0.34.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "17cffbe740121affb56fad0fc0e421804adf0ae00891205213b5cecd30db881d"
[[package]]
name = "windows_i686_gnu"
version = "0.34.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2564fde759adb79129d9b4f54be42b32c89970c18ebf93124ca8870a498688ed"
[[package]]
name = "windows_i686_msvc"
version = "0.34.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9cd9d32ba70453522332c14d38814bceeb747d80b3958676007acadd7e166956"
[[package]]
name = "windows_x86_64_gnu"
version = "0.34.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cfce6deae227ee8d356d19effc141a509cc503dfd1f850622ec4b0f84428e1f4"
[[package]]
name = "windows_x86_64_msvc"
version = "0.34.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d19538ccc21819d01deaf88d6a17eae6596a12e9aafdbb97916fb49896d89de9"

View file

@ -0,0 +1,10 @@
[package]
name = "tgsa"
version = "0.1.0"
edition = "2021"
[dependencies]
anyhow = "1.0"
crimp = "0.2"
scraper = "0.12"
url = "2.2"

View file

@ -0,0 +1,10 @@
{ depot, pkgs, ... }:
depot.third_party.naersk.buildPackage {
src = ./.;
buildInputs = with pkgs; [
pkgconfig
openssl
];
}

View file

@ -0,0 +1,140 @@
use anyhow::{anyhow, Context, Result};
#[derive(Debug)]
struct TgLink {
username: String,
message_id: usize,
}
impl TgLink {
fn to_url(&self) -> String {
format!("https://t.me/{}/{}?embed=1", self.username, self.message_id)
}
}
fn fetch_embed(link: &TgLink) -> Result<String> {
let response = crimp::Request::get(&link.to_url())
.send()
.context("failed to fetch embed data")?
.as_string()
.context("failed to decode embed data")?
.error_for_status(|resp| {
anyhow!("telegram request failed: {} ({})", resp.body, resp.status)
})?;
Ok(response.body)
}
#[derive(Debug)]
struct TgMessage {
author: String,
message: Option<String>,
photos: Vec<String>,
}
fn extract_photo_url(style: &str) -> Option<&str> {
let url_start = style.find("url('")? + 5;
let url_end = style.find("')")?;
Some(&style[url_start..url_end])
}
fn parse_tgmessage(embed: &str) -> Result<TgMessage> {
use scraper::{Html, Selector};
let doc = Html::parse_document(embed);
let author_sel = Selector::parse("a.tgme_widget_message_owner_name").unwrap();
let author = doc
.select(&author_sel)
.next()
.ok_or_else(|| anyhow!("failed to find message author"))?
.text()
.collect::<Vec<&str>>()
.concat();
let msg_sel = Selector::parse("div.tgme_widget_message_text.js-message_text").unwrap();
let message = doc
.select(&msg_sel)
.next()
.map(|m| m.text().collect::<Vec<&str>>().concat());
let photo_sel = Selector::parse("a.tgme_widget_message_photo_wrap").unwrap();
let mut photos = vec![];
for photo in doc.select(&photo_sel) {
if let Some(style) = photo.value().attr("style") {
if let Some(url) = extract_photo_url(style) {
photos.push(url.to_string())
}
}
}
Ok(TgMessage {
author,
message,
photos,
})
}
fn shorten_photo_links(msg: &mut TgMessage) -> Result<()> {
let mut url = url::Url::parse("https://tinyurl.com/api-create.php")?;
let mut shortened = vec![];
for photo in &msg.photos {
url.query_pairs_mut().clear().append_pair("url", &photo);
let request = url.as_str();
let response = crimp::Request::get(request)
.send()
.context("failed to shorten URL")?
.as_string()
.context("failed to decode shortened URL")?
.error_for_status(|resp| {
anyhow!("tinyurl request failed: {} ({})", resp.body, resp.status)
})?;
shortened.push(response.body.trim().into());
}
msg.photos = shortened;
Ok(())
}
fn to_bbcode(link: &TgLink, msg: &TgMessage) -> String {
let mut out = String::new();
out.push_str(&format!("[quote=\"{}\"]\n", msg.author));
for photo in &msg.photos {
out.push_str(&format!("[timg]{}[/timg]\n", photo));
}
if let Some(message) = &msg.message {
out.push_str(message);
}
out.push_str("\n[/quote]\n");
out.push_str(&format!(
"[i](via [url=\"{}\"]Telegram[/url])[/i]",
link.to_url(),
));
return out;
}
fn main() {
crimp::init();
let link = TgLink {
username: "RWApodcast".into(),
message_id: 113,
};
let embed = fetch_embed(&link).unwrap();
let mut msg = parse_tgmessage(&embed).unwrap();
shorten_photo_links(&mut msg).unwrap();
println!("{}", to_bbcode(&link, &msg));
}