feat: work with docs/xls and simple html (#1526)

2025-03-10 10:29:00 +11:00
parent 3faff03f7c
commit 602300c61f
9 changed files with 2229 additions and 5 deletions
@@ -35,6 +35,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e89da841a80418a9b391ebaea17f5c112ffaaa96f621d2c285b5174da76b9011"
 dependencies = [
 "cfg-if",
+ "getrandom 0.2.15",
 "once_cell",
 "version_check",
 "zerocopy",
@@ -167,6 +168,9 @@ name = "arbitrary"
 version = "1.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "dde20b3d026af13f561bdd0f15edf01fc734f0dafcedbaf42bba506a9517f223"
+dependencies = [
+ "derive_arbitrary",
+]

 [[package]]
 name = "arg_enum_proc_macro"
@@ -897,6 +901,21 @@ dependencies = [
 "which",
 ]

+[[package]]
+name = "bit-set"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "08807e080ed7f9d5433fa9b275196cfc35414f66a0c79d864dc51a0d825231a3"
+dependencies = [
+ "bit-vec",
+]
+
+[[package]]
+name = "bit-vec"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5e764a1d40d510daf35e07be9eb06e75770908c27d411ee6c92109c9840eaaf7"
+
 [[package]]
 name = "bit_field"
 version = "0.10.2"
@@ -1097,6 +1116,17 @@ dependencies = [
 "nom",
 ]

+[[package]]
+name = "cfb"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d8a4f8e55be323b378facfcf1f06aa97f6ec17cf4ac84fb17325093aaf62da41"
+dependencies = [
+ "byteorder",
+ "fnv",
+ "uuid",
+]
+
 [[package]]
 name = "cfg-expr"
 version = "0.15.8"
@@ -1642,6 +1672,17 @@ dependencies = [
 "serde",
 ]

+[[package]]
+name = "derive_arbitrary"
+version = "1.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "30542c1ad912e0e3d22a1935c290e12e8a29d704a420177a31faad4a601a0800"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.99",
+]
+
 [[package]]
 name = "derive_builder"
 version = "0.20.2"
@@ -1746,6 +1787,12 @@ dependencies = [
 "const-random",
 ]

+[[package]]
+name = "doc-comment"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fea41bba32d969b513997752735605054bc0dfa92b4c56bf1189f2e174be7a10"
+
 [[package]]
 name = "document-features"
 version = "0.2.11"
@@ -1755,6 +1802,21 @@ dependencies = [
 "litrs",
 ]

+[[package]]
+name = "docx-rs"
+version = "0.4.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e593b51d4fe95d69d70fd40da4b314b029736302c986c3c760826e842fd27dc3"
+dependencies = [
+ "base64 0.13.1",
+ "image 0.24.9",
+ "serde",
+ "serde_json",
+ "thiserror 1.0.69",
+ "xml-rs",
+ "zip 0.6.6",
+]
+
 [[package]]
 name = "dotenv"
 version = "0.15.0"
@@ -1873,6 +1935,17 @@ dependencies = [
 "zune-inflate",
 ]

+[[package]]
+name = "fancy-regex"
+version = "0.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6e24cb5a94bcae1e5408b0effca5cd7172ea3c5755049c5f3af4cd283a165298"
+dependencies = [
+ "bit-set",
+ "regex-automata 0.4.9",
+ "regex-syntax 0.8.5",
+]
+
 [[package]]
 name = "fastrand"
 version = "2.3.0"
@@ -2310,10 +2383,12 @@ dependencies = [
 "async-trait",
 "base64 0.21.7",
 "chrono",
+ "docx-rs",
 "etcetera",
 "google-drive3",
 "http-body-util",
 "ignore",
+ "image 0.24.9",
 "include_dir",
 "indoc",
 "kill_tree",
@@ -2329,13 +2404,13 @@ dependencies = [
 "serial_test",
 "shellexpand",
 "sysinfo 0.32.1",
- "temp-env",
 "tempfile",
 "thiserror 1.0.69",
 "tokio",
 "tracing",
 "tracing-appender",
 "tracing-subscriber",
+ "umya-spreadsheet",
 "url",
 "urlencoding",
 "webbrowser",
@@ -2512,6 +2587,21 @@ dependencies = [
 "windows-sys 0.59.0",
 ]

+[[package]]
+name = "html_parser"
+version = "0.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f6f56db07b6612644f6f7719f8ef944f75fff9d6378fdf3d316fd32194184abd"
+dependencies = [
+ "doc-comment",
+ "pest",
+ "pest_derive",
+ "serde",
+ "serde_derive",
+ "serde_json",
+ "thiserror 1.0.69",
+]
+
 [[package]]
 name = "http"
 version = "0.2.12"
@@ -2875,6 +2965,24 @@ dependencies = [
 "winapi-util",
 ]

+[[package]]
+name = "image"
+version = "0.24.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5690139d2f55868e080017335e4b94cb7414274c74f1669c84fb5feba2c9f69d"
+dependencies = [
+ "bytemuck",
+ "byteorder",
+ "color_quant",
+ "exr",
+ "gif",
+ "jpeg-decoder",
+ "num-traits",
+ "png",
+ "qoi",
+ "tiff",
+]
+
 [[package]]
 name = "image"
 version = "0.25.5"
@@ -3096,6 +3204,9 @@ name = "jpeg-decoder"
 version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f5d4a7da358eff58addd2877a45865158f0d78c911d43a5784ceb7bbf52833b0"
+dependencies = [
+ "rayon",
+]

 [[package]]
 name = "js-sys"
@@ -3280,6 +3391,12 @@ dependencies = [
 "scopeguard",
 ]

+[[package]]
+name = "lockfree-object-pool"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9374ef4228402d4b7e403e5838cb880d9ee663314b0a900d5a6aabf0c213552e"
+
 [[package]]
 name = "log"
 version = "0.4.26"
@@ -4220,6 +4337,16 @@ dependencies = [
 "memchr",
 ]

+[[package]]
+name = "quick-xml"
+version = "0.37.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "165859e9e55f79d67b96c5d96f4e88b6f2695a1972849c15a6a3f5c59fc2c003"
+dependencies = [
+ "memchr",
+ "serde",
+]
+
 [[package]]
 name = "quinn"
 version = "0.11.6"
@@ -5459,6 +5586,12 @@ dependencies = [
 "unicode-width 0.2.0",
 ]

+[[package]]
+name = "thin-vec"
+version = "0.2.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a38c90d48152c236a3ab59271da4f4ae63d678c5d7ad6b7714d7cb9760be5e4b"
+
 [[package]]
 name = "thiserror"
 version = "1.0.69"
@@ -5499,6 +5632,12 @@ dependencies = [
 "syn 2.0.99",
 ]

+[[package]]
+name = "thousands"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3bf63baf9f5039dadc247375c29eb13706706cfde997d0330d05aa63a77d8820"
+
 [[package]]
 name = "thread_local"
 version = "1.1.8"
@@ -5942,6 +6081,35 @@ version = "0.1.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2896d95c02a80c6d6a5d6e953d479f5ddf2dfdb6a244441010e373ac0fb88971"

+[[package]]
+name = "umya-spreadsheet"
+version = "2.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "17ec15f1f191ba42ba0ed0f788999eec910c201cbbd4ae5de7cf0eb0a94b3d1a"
+dependencies = [
+ "aes",
+ "ahash",
+ "base64 0.22.1",
+ "byteorder",
+ "cbc",
+ "cfb",
+ "chrono",
+ "encoding_rs",
+ "fancy-regex",
+ "getrandom 0.2.15",
+ "hmac",
+ "html_parser",
+ "image 0.25.5",
+ "lazy_static",
+ "md-5",
+ "quick-xml 0.37.2",
+ "regex",
+ "sha2",
+ "thin-vec",
+ "thousands",
+ "zip 2.2.3",
+]
+
 [[package]]
 name = "unicode-ident"
 version = "1.0.18"
@@ -6783,7 +6951,7 @@ dependencies = [
 "core-foundation 0.10.0",
 "core-graphics",
 "dbus",
- "image",
+ "image 0.25.5",
 "log",
 "percent-encoding",
 "sysinfo 0.32.1",
@@ -6803,6 +6971,12 @@ dependencies = [
 "quick-xml 0.30.0",
 ]

+[[package]]
+name = "xml-rs"
+version = "0.8.25"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c5b940ebc25896e71dd073bad2dbaa2abfe97b0a391415e22ad1326d9c54e3c4"
+
 [[package]]
 name = "xmlparser"
 version = "0.13.6"
@@ -6964,6 +7138,49 @@ dependencies = [
 "syn 2.0.99",
 ]

+[[package]]
+name = "zip"
+version = "0.6.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "760394e246e4c28189f19d488c058bf16f564016aefac5d32bb1f3b51d5e9261"
+dependencies = [
+ "byteorder",
+ "crc32fast",
+ "crossbeam-utils",
+ "flate2",
+]
+
+[[package]]
+name = "zip"
+version = "2.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b280484c454e74e5fff658bbf7df8fdbe7a07c6b2de4a53def232c15ef138f3a"
+dependencies = [
+ "arbitrary",
+ "crc32fast",
+ "crossbeam-utils",
+ "displaydoc",
+ "flate2",
+ "indexmap 2.7.1",
+ "memchr",
+ "thiserror 2.0.12",
+ "zopfli",
+]
+
+[[package]]
+name = "zopfli"
+version = "0.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e5019f391bac5cf252e93bbcc53d039ffd62c7bfb7c150414d61369afe57e946"
+dependencies = [
+ "bumpalo",
+ "crc32fast",
+ "lockfree-object-pool",
+ "log",
+ "once_cell",
+ "simd-adler32",
+]
+
 [[package]]
 name = "zstd"
 version = "0.13.3"