web: fetch pdf text by pages
This commit is contained in:
Generated
+270
-3
@@ -11,6 +11,32 @@ dependencies = [
|
||||
"gimli",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "adler2"
|
||||
version = "2.0.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa"
|
||||
|
||||
[[package]]
|
||||
name = "adobe-cmap-parser"
|
||||
version = "0.4.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "ae8abfa9a4688de8fc9f42b3f013b6fffec18ed8a554f5f113577e0b9b3212a3"
|
||||
dependencies = [
|
||||
"pom",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "aes"
|
||||
version = "0.8.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b169f7a6d4742236a0a00c541b845991d0ac43e546831af1249753ab4c3aa3a0"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"cipher",
|
||||
"cpufeatures 0.2.17",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "aho-corasick"
|
||||
version = "1.1.4"
|
||||
@@ -221,6 +247,15 @@ dependencies = [
|
||||
"hybrid-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 = "bstr"
|
||||
version = "1.12.1"
|
||||
@@ -241,6 +276,12 @@ dependencies = [
|
||||
"allocator-api2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "bytecount"
|
||||
version = "0.6.9"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "175812e0be2bccb6abe50bb8d566126198344f707e304f45c648fd8f2cc0365e"
|
||||
|
||||
[[package]]
|
||||
name = "bytemuck"
|
||||
version = "1.25.0"
|
||||
@@ -262,6 +303,15 @@ dependencies = [
|
||||
"rustversion",
|
||||
]
|
||||
|
||||
[[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 = "1.2.59"
|
||||
@@ -280,6 +330,12 @@ version = "1.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6d43a04d8753f35258c91f8ec639f792891f748a1edbd759cf1dcea3382ad83c"
|
||||
|
||||
[[package]]
|
||||
name = "cff-parser"
|
||||
version = "0.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "31f5b6e9141c036f3ff4ce7b2f7e432b0f00dee416ddcd4f17741d189ddc2e9d"
|
||||
|
||||
[[package]]
|
||||
name = "cfg-if"
|
||||
version = "1.0.4"
|
||||
@@ -306,6 +362,16 @@ dependencies = [
|
||||
"windows-link",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "cipher"
|
||||
version = "0.4.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "773f3b9af64447d2ce9850330c473515014aa235e6a783b02db81ff39e4a3dad"
|
||||
dependencies = [
|
||||
"crypto-common 0.1.7",
|
||||
"inout",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "clap"
|
||||
version = "4.6.0"
|
||||
@@ -881,6 +947,15 @@ 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 = "either"
|
||||
version = "1.15.0"
|
||||
@@ -944,6 +1019,15 @@ dependencies = [
|
||||
"windows-sys 0.61.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "euclid"
|
||||
version = "0.20.14"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "2bb7ef65b3777a325d1eeefefab5b6d4959da54747e33bd6258e789640f307ad"
|
||||
dependencies = [
|
||||
"num-traits",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "euclid"
|
||||
version = "0.22.14"
|
||||
@@ -960,7 +1044,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "74fef4569247a5f429d9156b9d0a2599914385dd189c539334c625d8099d90ab"
|
||||
dependencies = [
|
||||
"futures-core",
|
||||
"nom",
|
||||
"nom 7.1.3",
|
||||
"pin-project-lite",
|
||||
]
|
||||
|
||||
@@ -1020,6 +1104,16 @@ version = "0.4.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0ce7134b9999ecaf8bcd65542e436736ef32ddca1b3e06094cb6ec5755203b80"
|
||||
|
||||
[[package]]
|
||||
name = "flate2"
|
||||
version = "1.1.9"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "843fba2746e448b37e26a819579957415c8cef339bf08564fe8b7ddbd959573c"
|
||||
dependencies = [
|
||||
"crc32fast",
|
||||
"miniz_oxide",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "fnv"
|
||||
version = "1.0.7"
|
||||
@@ -1704,6 +1798,16 @@ dependencies = [
|
||||
"rustversion",
|
||||
]
|
||||
|
||||
[[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 = "instability"
|
||||
version = "0.3.12"
|
||||
@@ -1965,6 +2069,34 @@ version = "0.4.29"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5e5032e24019045c762d3c0f28f5b6b8bbf38563a65908389bf7978758920897"
|
||||
|
||||
[[package]]
|
||||
name = "lopdf"
|
||||
version = "0.38.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c7184fdea2bc3cd272a1acec4030c321a8f9875e877b3f92a53f2f6033fdc289"
|
||||
dependencies = [
|
||||
"aes",
|
||||
"bitflags 2.11.0",
|
||||
"cbc",
|
||||
"ecb",
|
||||
"encoding_rs",
|
||||
"flate2",
|
||||
"getrandom 0.3.4",
|
||||
"indexmap",
|
||||
"itoa",
|
||||
"log",
|
||||
"md-5",
|
||||
"nom 8.0.0",
|
||||
"nom_locate",
|
||||
"rand 0.9.4",
|
||||
"rangemap",
|
||||
"sha2 0.10.9",
|
||||
"stringprep",
|
||||
"thiserror 2.0.18",
|
||||
"ttf-parser",
|
||||
"weezl",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "lru"
|
||||
version = "0.16.3"
|
||||
@@ -2091,6 +2223,16 @@ dependencies = [
|
||||
"tokio",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "md-5"
|
||||
version = "0.10.6"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d89e7ee0cfbedfc4da3340218492196241d89eefb6dab27de5df917a6d2e78cf"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"digest 0.10.7",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "memchr"
|
||||
version = "2.8.0"
|
||||
@@ -2180,6 +2322,16 @@ version = "0.2.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
|
||||
|
||||
[[package]]
|
||||
name = "miniz_oxide"
|
||||
version = "0.8.9"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1fa76a2c86f704bdb222d66965fb3d63269ce38518b83cb0575fca855ebb6316"
|
||||
dependencies = [
|
||||
"adler2",
|
||||
"simd-adler32",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "mio"
|
||||
version = "1.2.0"
|
||||
@@ -2271,6 +2423,26 @@ dependencies = [
|
||||
"minimal-lexical",
|
||||
]
|
||||
|
||||
[[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 8.0.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "nu-ansi-term"
|
||||
version = "0.50.3"
|
||||
@@ -2440,6 +2612,23 @@ dependencies = [
|
||||
"windows-link",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pdf-extract"
|
||||
version = "0.10.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1e28ba1758a3d3f361459645780e09570b573fc3c82637449e9963174c813a98"
|
||||
dependencies = [
|
||||
"adobe-cmap-parser",
|
||||
"cff-parser",
|
||||
"encoding_rs",
|
||||
"euclid 0.20.14",
|
||||
"log",
|
||||
"lopdf",
|
||||
"postscript",
|
||||
"type1-encoding-parser",
|
||||
"unicode-normalization",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "percent-encoding"
|
||||
version = "2.3.2"
|
||||
@@ -2666,6 +2855,12 @@ dependencies = [
|
||||
"thiserror 2.0.18",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pom"
|
||||
version = "1.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "60f6ce597ecdcc9a098e7fddacb1065093a3d66446fa16c675e7e71d1b5c28e6"
|
||||
|
||||
[[package]]
|
||||
name = "portable-atomic"
|
||||
version = "1.13.1"
|
||||
@@ -2684,6 +2879,12 @@ dependencies = [
|
||||
"serde",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "postscript"
|
||||
version = "0.14.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "78451badbdaebaf17f053fd9152b3ffb33b516104eacb45e7864aaa9c712f306"
|
||||
|
||||
[[package]]
|
||||
name = "potential_utf"
|
||||
version = "0.1.5"
|
||||
@@ -2939,6 +3140,12 @@ dependencies = [
|
||||
"getrandom 0.3.4",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "rangemap"
|
||||
version = "1.7.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "973443cf09a9c8656b574a866ab68dfa19f0867d0340648c7d2f6a71b8a8ea68"
|
||||
|
||||
[[package]]
|
||||
name = "ratatui"
|
||||
version = "0.30.0"
|
||||
@@ -3646,6 +3853,12 @@ dependencies = [
|
||||
"libc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "simd-adler32"
|
||||
version = "0.3.9"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "703d5c7ef118737c72f1af64ad2f6f8c5e1921f818cdcb97b8fe6fc69bf66214"
|
||||
|
||||
[[package]]
|
||||
name = "siphasher"
|
||||
version = "0.3.11"
|
||||
@@ -3736,6 +3949,17 @@ dependencies = [
|
||||
"quote",
|
||||
]
|
||||
|
||||
[[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"
|
||||
@@ -3884,7 +4108,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d4ea810f0692f9f51b382fff5893887bb4580f5fa246fde546e0b13e7fcee662"
|
||||
dependencies = [
|
||||
"fnv",
|
||||
"nom",
|
||||
"nom 7.1.3",
|
||||
"phf 0.11.3",
|
||||
"phf_codegen 0.11.3",
|
||||
]
|
||||
@@ -4179,6 +4403,7 @@ dependencies = [
|
||||
"llm-worker",
|
||||
"manifest",
|
||||
"markup5ever_rcdom",
|
||||
"pdf-extract",
|
||||
"reqwest",
|
||||
"schemars",
|
||||
"secrets",
|
||||
@@ -4318,6 +4543,12 @@ dependencies = [
|
||||
"toml",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ttf-parser"
|
||||
version = "0.25.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d2df906b07856748fa3f6e0ad0cbaa047052d4a7dd609e231c4f72cee8c36f31"
|
||||
|
||||
[[package]]
|
||||
name = "tui"
|
||||
version = "0.1.0"
|
||||
@@ -4346,6 +4577,15 @@ dependencies = [
|
||||
"uuid",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "type1-encoding-parser"
|
||||
version = "0.1.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "fa10c302f5a53b7ad27fd42a3996e23d096ba39b5b8dd6d9e683a05b01bee749"
|
||||
dependencies = [
|
||||
"pom",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "typeid"
|
||||
version = "1.0.3"
|
||||
@@ -4370,12 +4610,33 @@ version = "2.9.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "dbc4bc3a9f746d862c45cb89d705aa10f187bb96c76001afab07a0d35ce60142"
|
||||
|
||||
[[package]]
|
||||
name = "unicode-bidi"
|
||||
version = "0.3.18"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5c1cb5db39152898a79168971543b1cb5020dff7fe43c8dc468b0885f5e29df5"
|
||||
|
||||
[[package]]
|
||||
name = "unicode-ident"
|
||||
version = "1.0.24"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
|
||||
|
||||
[[package]]
|
||||
name = "unicode-normalization"
|
||||
version = "0.1.25"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5fd4f6878c9cb28d874b009da9e8d183b5abc80117c40bbd187a1fde336be6e8"
|
||||
dependencies = [
|
||||
"tinyvec",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "unicode-properties"
|
||||
version = "0.1.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7df058c713841ad818f1dc5d3fd88063241cc61f49f5fbea4b951e8cf5a8d71d"
|
||||
|
||||
[[package]]
|
||||
name = "unicode-segmentation"
|
||||
version = "1.13.2"
|
||||
@@ -5011,6 +5272,12 @@ 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 = "wezterm-bidi"
|
||||
version = "0.2.3"
|
||||
@@ -5077,7 +5344,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7012add459f951456ec9d6c7e6fc340b1ce15d6fc9629f8c42853412c029e57e"
|
||||
dependencies = [
|
||||
"bitflags 1.3.2",
|
||||
"euclid",
|
||||
"euclid 0.22.14",
|
||||
"lazy_static",
|
||||
"serde",
|
||||
"wezterm-dynamic",
|
||||
|
||||
Reference in New Issue
Block a user