pdfgutter: two facing pages photographed as one, found and cut

This commit is contained in:
funkpower
2026-09-19 15:19:35 -04:00
parent 49f12c9718
commit 3c697bee50
17 changed files with 2374 additions and 13 deletions
Generated
+371 -12
View File
@@ -8,6 +8,17 @@ version = "2.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa"
[[package]]
name = "aes"
version = "0.8.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b169f7a6d4742236a0a00c541b845991d0ac43e546831af1249753ab4c3aa3a0"
dependencies = [
"cfg-if",
"cipher",
"cpufeatures",
]
[[package]]
name = "aho-corasick"
version = "1.1.5"
@@ -130,6 +141,30 @@ version = "0.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5e764a1d40d510daf35e07be9eb06e75770908c27d411ee6c92109c9840eaaf7"
[[package]]
name = "bitflags"
version = "2.13.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3ded4057c258ba199e2d26386d3af3780957ecaee6c4ef4041c6b4b8b97c0b06"
[[package]]
name = "block-buffer"
version = "0.10.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71"
dependencies = [
"generic-array",
]
[[package]]
name = "block-padding"
version = "0.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a8894febbff9f758034a5b8e12d87918f56dfc64a8e1fe757d65e29041538d93"
dependencies = [
"generic-array",
]
[[package]]
name = "booksniff"
version = "0.1.0"
@@ -152,6 +187,12 @@ dependencies = [
"serde_core",
]
[[package]]
name = "bytecount"
version = "0.6.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "175812e0be2bccb6abe50bb8d566126198344f707e304f45c648fd8f2cc0365e"
[[package]]
name = "bytes"
version = "1.12.1"
@@ -167,6 +208,15 @@ dependencies = [
"serde",
]
[[package]]
name = "cbc"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "26b52a9543ae338f279b96b0b9fed9c8093744685043739079ce85cd58f289a6"
dependencies = [
"cipher",
]
[[package]]
name = "cc"
version = "1.4.7"
@@ -195,6 +245,16 @@ dependencies = [
"textkit",
]
[[package]]
name = "cipher"
version = "0.4.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "773f3b9af64447d2ce9850330c473515014aa235e6a783b02db81ff39e4a3dad"
dependencies = [
"crypto-common",
"inout",
]
[[package]]
name = "clap"
version = "4.6.7"
@@ -226,7 +286,7 @@ dependencies = [
"heck",
"proc-macro2",
"quote",
"syn",
"syn 3.0.6",
]
[[package]]
@@ -280,6 +340,15 @@ dependencies = [
"thiserror",
]
[[package]]
name = "cpufeatures"
version = "0.2.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280"
dependencies = [
"libc",
]
[[package]]
name = "crc32fast"
version = "1.5.2"
@@ -289,6 +358,16 @@ dependencies = [
"cfg-if",
]
[[package]]
name = "crypto-common"
version = "0.1.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "78c8292055d1c1df0cce5d180393dc8cce0abec0a7102adb6c7b1eef6016d60a"
dependencies = [
"generic-array",
"typenum",
]
[[package]]
name = "cuekit"
version = "0.1.0"
@@ -353,6 +432,16 @@ version = "1.6.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "abd57806937c9cc163efc8ea3910e00a62e2aeb0b8119f1793a978088f8f6b04"
[[package]]
name = "digest"
version = "0.10.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
dependencies = [
"block-buffer",
"crypto-common",
]
[[package]]
name = "displaydoc"
version = "0.2.7"
@@ -361,7 +450,7 @@ checksum = "c6232dd377dcc64799954cbd3a9bb882e9cdc1308ccd87b1c098f1fb2eaf82a8"
dependencies = [
"proc-macro2",
"quote",
"syn",
"syn 3.0.6",
]
[[package]]
@@ -379,6 +468,15 @@ version = "1.0.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d0881ea181b1df73ff77ffaaf9c7544ecc11e82fba9b5f27b262a3c73a332555"
[[package]]
name = "ecb"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1a8bfa975b1aec2145850fcaa1c6fe269a16578c44705a532ae3edc92b8881c7"
dependencies = [
"cipher",
]
[[package]]
name = "emb"
version = "0.1.0"
@@ -393,6 +491,15 @@ dependencies = [
"ureq",
]
[[package]]
name = "encoding_rs"
version = "0.8.35"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "75030f3c4f45dafd7586dd6780965a8c7e8e285a5ecb86713e63a79c5b2766f3"
dependencies = [
"cfg-if",
]
[[package]]
name = "equivalent"
version = "1.0.2"
@@ -447,6 +554,16 @@ dependencies = [
"percent-encoding",
]
[[package]]
name = "generic-array"
version = "0.14.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a"
dependencies = [
"typenum",
"version_check",
]
[[package]]
name = "getrandom"
version = "0.2.17"
@@ -458,6 +575,18 @@ dependencies = [
"wasi",
]
[[package]]
name = "getrandom"
version = "0.3.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "899def5c37c4fd7b2664648c28120ecec138e4d395b459e5ca34f9cce2dd77fd"
dependencies = [
"cfg-if",
"libc",
"r-efi",
"wasip2",
]
[[package]]
name = "hashbrown"
version = "0.17.1"
@@ -598,6 +727,16 @@ dependencies = [
"hashbrown",
]
[[package]]
name = "inout"
version = "0.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "879f10e63c20629ecabbb64a8010319738c66a5cd0c29b02d63d272b03751d01"
dependencies = [
"block-padding",
"generic-array",
]
[[package]]
name = "is_terminal_polyfill"
version = "1.70.2"
@@ -640,6 +779,44 @@ version = "0.4.34"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f9f8bd3e56ce4dfc153cf470fffbfa98c7620958b312ca5c3a4b8d5181fd13c6"
[[package]]
name = "lopdf"
version = "0.38.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c7184fdea2bc3cd272a1acec4030c321a8f9875e877b3f92a53f2f6033fdc289"
dependencies = [
"aes",
"bitflags",
"cbc",
"ecb",
"encoding_rs",
"flate2",
"getrandom 0.3.4",
"indexmap",
"itoa",
"log",
"md-5",
"nom",
"nom_locate",
"rand",
"rangemap",
"sha2",
"stringprep",
"thiserror",
"ttf-parser",
"weezl",
]
[[package]]
name = "md-5"
version = "0.10.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d89e7ee0cfbedfc4da3340218492196241d89eefb6dab27de5df917a6d2e78cf"
dependencies = [
"cfg-if",
"digest",
]
[[package]]
name = "mdscrub"
version = "0.1.0"
@@ -684,6 +861,26 @@ dependencies = [
"simd-adler32",
]
[[package]]
name = "nom"
version = "8.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "df9761775871bdef83bee530e60050f7e54b1105350d6884eb0fb4f46c2f9405"
dependencies = [
"memchr",
]
[[package]]
name = "nom_locate"
version = "5.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0b577e2d69827c4740cba2b52efaad1c4cc7c73042860b199710b3575c68438d"
dependencies = [
"bytecount",
"memchr",
"nom",
]
[[package]]
name = "num-conv"
version = "0.1.0"
@@ -716,12 +913,26 @@ dependencies = [
"cueseg",
"mdscrub",
"mdsplit",
"pdfgutter",
"pdftriage",
"rrf",
"serde_json",
"textkit",
]
[[package]]
name = "pdfgutter"
version = "0.1.0"
dependencies = [
"catena-cli",
"clap",
"corpus-core",
"lopdf",
"schemars",
"serde",
"serde_json",
]
[[package]]
name = "pdftriage"
version = "0.1.0"
@@ -756,6 +967,15 @@ version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "439ee305def115ba05938db6eb1644ff94165c5ab5e9420d1c1bcedbba909391"
[[package]]
name = "ppv-lite86"
version = "0.2.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "85eae3c4ed2f50dcfe72643da4befc30deadb458a9b590d720cde2f2b1e97da9"
dependencies = [
"zerocopy",
]
[[package]]
name = "proc-macro2"
version = "1.0.107"
@@ -774,6 +994,47 @@ dependencies = [
"proc-macro2",
]
[[package]]
name = "r-efi"
version = "5.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
[[package]]
name = "rand"
version = "0.9.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b9ef1d0d795eb7d84685bca4f72f3649f064e6641543d3a8c415898726a57b41"
dependencies = [
"rand_chacha",
"rand_core",
]
[[package]]
name = "rand_chacha"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
dependencies = [
"ppv-lite86",
"rand_core",
]
[[package]]
name = "rand_core"
version = "0.9.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "76afc826de14238e6e8c374ddcc1fa19e374fd8dd986b0d2af0d02377261d83c"
dependencies = [
"getrandom 0.3.4",
]
[[package]]
name = "rangemap"
version = "1.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a611d15b50743feb4c76b7d03edcb0e64f399c26961e4efe6975bc398be6aa3d"
[[package]]
name = "ref-cast"
version = "1.0.27"
@@ -791,7 +1052,7 @@ checksum = "92ecd8964f8453721699a1ed72037b0db49ce2f5a5138486ee89bed6f67cdf3a"
dependencies = [
"proc-macro2",
"quote",
"syn",
"syn 3.0.6",
]
[[package]]
@@ -831,7 +1092,7 @@ checksum = "a4689e6c2294d81e88dc6261c768b63bc4fcdb852be6d1352498b114f61383b7"
dependencies = [
"cc",
"cfg-if",
"getrandom",
"getrandom 0.2.17",
"libc",
"untrusted",
"windows-sys 0.52.0",
@@ -910,7 +1171,7 @@ dependencies = [
"proc-macro2",
"quote",
"serde_derive_internals",
"syn",
"syn 3.0.6",
]
[[package]]
@@ -940,7 +1201,7 @@ checksum = "e7a5d71263a5a7d47b41f6b3f06ba276f10cc18b0931f1799f710578e2309348"
dependencies = [
"proc-macro2",
"quote",
"syn",
"syn 3.0.6",
]
[[package]]
@@ -951,7 +1212,7 @@ checksum = "f852137cce035d6a4df67ccce505ff6b3e9fd3a10e3e52b24dc71e650bb1a9bd"
dependencies = [
"proc-macro2",
"quote",
"syn",
"syn 3.0.6",
]
[[package]]
@@ -967,6 +1228,17 @@ dependencies = [
"zmij",
]
[[package]]
name = "sha2"
version = "0.10.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
dependencies = [
"cfg-if",
"cpufeatures",
"digest",
]
[[package]]
name = "shlex"
version = "2.0.1"
@@ -991,6 +1263,17 @@ version = "1.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6ce2be8dc25455e1f91df71bfa12ad37d7af1092ae736f3a6cd0e37bc7810596"
[[package]]
name = "stringprep"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7b4df3d392d81bd458a8a621b8bffbd2302a12ffe288a9d931670948749463b1"
dependencies = [
"unicode-bidi",
"unicode-normalization",
"unicode-properties",
]
[[package]]
name = "strsim"
version = "0.11.1"
@@ -1003,6 +1286,17 @@ version = "2.6.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292"
[[package]]
name = "syn"
version = "2.0.119"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "872831b642d1a07999a962a351ed35b955ea2cfc8f3862091e2a240a84f17297"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "syn"
version = "3.0.6"
@@ -1022,7 +1316,7 @@ checksum = "901704edd0dfe137f1987838ee4f259e4e063c31371bdb423f7ae38ec6f77f02"
dependencies = [
"proc-macro2",
"quote",
"syn",
"syn 3.0.6",
]
[[package]]
@@ -1050,7 +1344,7 @@ checksum = "bc04cd3e1236dd4a98afca4569f2deb3f120e5422a4023be2cb683f8486292af"
dependencies = [
"proc-macro2",
"quote",
"syn",
"syn 3.0.6",
]
[[package]]
@@ -1115,6 +1409,24 @@ version = "1.13.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fd3ca314f692efd6c868f8408f53fe444634a845f96c028b97d35f6a1f79f0ee"
[[package]]
name = "ttf-parser"
version = "0.25.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d2df906b07856748fa3f6e0ad0cbaa047052d4a7dd609e231c4f72cee8c36f31"
[[package]]
name = "typenum"
version = "1.20.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6f5e870be6c3b371b77fe0ee0bafb859fa4964b4404c27de1d380043c4dda20"
[[package]]
name = "unicode-bidi"
version = "0.3.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5c1cb5db39152898a79168971543b1cb5020dff7fe43c8dc468b0885f5e29df5"
[[package]]
name = "unicode-general-category"
version = "1.1.0"
@@ -1136,6 +1448,12 @@ dependencies = [
"tinyvec",
]
[[package]]
name = "unicode-properties"
version = "0.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7df058c713841ad818f1dc5d3fd88063241cc61f49f5fbea4b951e8cf5a8d71d"
[[package]]
name = "untrusted"
version = "0.9.0"
@@ -1216,6 +1534,15 @@ version = "0.11.1+wasi-snapshot-preview1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ccf3ec651a847eb01de73ccad15eb7d99f80485de043efb2f370cd654f4ea44b"
[[package]]
name = "wasip2"
version = "1.0.1+wasi-0.2.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0562428422c63773dad2c345a1882263bbf4d65cf3f42e90921f787ef5ad58e7"
dependencies = [
"wit-bindgen",
]
[[package]]
name = "webpki-roots"
version = "1.0.9"
@@ -1225,6 +1552,12 @@ dependencies = [
"rustls-pki-types",
]
[[package]]
name = "weezl"
version = "0.1.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a28ac98ddc8b9274cb41bb4d9d4d5c425b6020c50c46f25559911905610b4a88"
[[package]]
name = "windows-link"
version = "0.2.1"
@@ -1313,6 +1646,12 @@ version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
[[package]]
name = "wit-bindgen"
version = "0.46.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f17a85883d4e6d00e8a97c586de764dabcc06133f7f1d55dce5cdc070ad7fe59"
[[package]]
name = "writeable"
version = "0.6.4"
@@ -1338,10 +1677,30 @@ checksum = "33811428bee40dbceb6d545e95754741d17a6aef9a4849f0fd62e2ba4f412a78"
dependencies = [
"proc-macro2",
"quote",
"syn",
"syn 3.0.6",
"synstructure",
]
[[package]]
name = "zerocopy"
version = "0.8.57"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d35102a9f36d089ccae9e4c6802bc118be4487b80aaffc0ab4e0cf5ce92d2873"
dependencies = [
"zerocopy-derive",
]
[[package]]
name = "zerocopy-derive"
version = "0.8.57"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "146c01f5ab44258da43cf276c74a2763db2ff3969c9c652c3f2de07041d0b2bc"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.119",
]
[[package]]
name = "zerofrom"
version = "0.1.8"
@@ -1359,7 +1718,7 @@ checksum = "f75b4683f6c7f45248d4d64056a24298c6281e0993356d7d1b4a1a962ef10d4a"
dependencies = [
"proc-macro2",
"quote",
"syn",
"syn 3.0.6",
"synstructure",
]
@@ -1399,7 +1758,7 @@ checksum = "34df6fc39dbd26ddc9c10e6a2984476e13acce22e64e4487636ef494369225da"
dependencies = [
"proc-macro2",
"quote",
"syn",
"syn 3.0.6",
]
[[package]]