feat(repository): add language statistics analysis feature

- Remove data directory from gitignore to include language data
- Add build script to parse linguist languages.yml and generate static mappings
- Include serde and serde_yml dependencies for YAML parsing
- Add lang_stats module with language detection and statistics calculation
- Generate protobuf definitions for language statistics API endpoints
- Implement GetLanguageStats RPC endpoint in repository server
- Add comprehensive test suite for language statistics functionality
- Include extension and filename based language detection logic
- Implement binary file classification and group resolution features
This commit is contained in:
zhenyi
2026-06-10 13:06:59 +08:00
parent 9a0c26e5f6
commit 939931acad
10 changed files with 10202 additions and 1 deletions
Generated
+32
View File
@@ -699,6 +699,7 @@ dependencies = [
"ractor_cluster",
"serde",
"serde_json",
"serde_yml",
"sha2",
"tempfile",
"thiserror",
@@ -1892,6 +1893,16 @@ version = "0.2.186"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "68ab91017fe16c622486840e4c83c9a37afeff978bd239b5293d61ece587de66"
[[package]]
name = "libyml"
version = "0.0.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3302702afa434ffa30847a83305f0a69d6abd74293b6554c18ec85c7ef30c980"
dependencies = [
"anyhow",
"version_check",
]
[[package]]
name = "linux-raw-sys"
version = "0.12.1"
@@ -2518,6 +2529,12 @@ version = "1.0.22"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
[[package]]
name = "ryu"
version = "1.0.23"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9774ba4a74de5f7b1c1451ed6cd5285a32eddb5cccb8cc655a4e50009e06477f"
[[package]]
name = "same-file"
version = "1.0.6"
@@ -2582,6 +2599,21 @@ dependencies = [
"zmij",
]
[[package]]
name = "serde_yml"
version = "0.0.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "59e2dd588bf1597a252c3b920e0143eb99b0f76e4e082f4c92ce34fbc9e71ddd"
dependencies = [
"indexmap",
"itoa",
"libyml",
"memchr",
"ryu",
"serde",
"version_check",
]
[[package]]
name = "sha1"
version = "0.10.6"