PyPI - cc-transcript - Versions diffs - 0.3.0__tar.gz → 0.4.0__tar.gz - Mend

cc-transcript 0.3.0tar.gz → 0.4.0tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (39) hide show

{cc_transcript-0.3.0 → cc_transcript-0.4.0}/Cargo.lock RENAMED Viewed

@@ -2,6 +2,12 @@
 # It is not intended for manual editing.
 version = 4
+[[package]]
+name = "adler2"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa"
 [[package]]
 name = "ahash"
 version = "0.8.12"
@@ -9,7 +15,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
 dependencies = [
  "cfg-if",
- "getrandom",
+ "getrandom 0.3.4",
  "once_cell",
  "version_check",
  "zerocopy",
@@ -30,6 +36,12 @@ version = "1.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f2032f911046de80f0a198e0901378627c33f59ea0ac00e363d481118bd70a53"
+[[package]]
+name = "base64"
+version = "0.22.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
 [[package]]
 name = "bumpalo"
 version = "3.20.3"
@@ -42,12 +54,23 @@ version = "1.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1e748733b7cbc798e1434b6ac524f0c1ff2ab456fe201501e6497c8417a4fc33"
+[[package]]
+name = "cc"
+version = "1.2.63"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "556e016178bb5662a08681bbe0f00f8e17631781a4dfc8c45e466e4b185ec27f"
+dependencies = [
+ "find-msvc-tools",
+ "shlex",
+]
 [[package]]
 name = "cc_transcript_parser"
-version = "0.3.0"
+version = "0.4.0"
 dependencies = [
  "chrono",
  "crossbeam-channel",
+ "dirs",
  "memchr",
  "num_cpus",
  "once_cell",
@@ -56,6 +79,7 @@ dependencies = [
  "regex",
  "serde",
  "sonic-rs",
+ "udpipe-rs",
 ]
 [[package]]
@@ -73,6 +97,15 @@ dependencies = [
  "num-traits",
 ]
+[[package]]
+name = "crc32fast"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9481c1c90cbf2ac953f07c8d4a58aa3945c425b7185c9154d67a65e4230da511"
+dependencies = [
+ "cfg-if",
+]
 [[package]]
 name = "crossbeam-channel"
 version = "0.5.15"
@@ -107,6 +140,27 @@ version = "0.8.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
+[[package]]
+name = "dirs"
+version = "5.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "44c45a9d03d6676652bcb5e724c7e988de1acad23a711b5217ab9cbecbec2225"
+dependencies = [
+ "dirs-sys",
+]
+[[package]]
+name = "dirs-sys"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "520f05a5cbd335fae5a99ff7a6ab8627577660ee5cfd6a94a6a929b52ff0321c"
+dependencies = [
+ "libc",
+ "option-ext",
+ "redox_users",
+ "windows-sys 0.48.0",
+]
 [[package]]
 name = "either"
 version = "1.16.0"
@@ -131,6 +185,22 @@ dependencies = [
  "simdutf8",
 ]
+[[package]]
+name = "find-msvc-tools"
+version = "0.1.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582"
+[[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 = "futures-core"
 version = "0.3.32"
@@ -155,6 +225,17 @@ dependencies = [
  "slab",
 ]
+[[package]]
+name = "getrandom"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ff2abc00be7fca6ebc474524697ae276ad847ad0a6b3faa4bcb027e9a4614ad0"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "wasi",
+]
 [[package]]
 name = "getrandom"
 version = "0.3.4"
@@ -185,6 +266,22 @@ version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fc0fef456e4baa96da950455cd02c081ca953b141298e41db3fc7e36b1da849c"
+[[package]]
+name = "http"
+version = "1.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6970f50e31d6fc17d3fa27329444bfa74e196cf62e95052a3f6fee181dba6425"
+dependencies = [
+ "bytes",
+ "itoa",
+]
+[[package]]
+name = "httparse"
+version = "1.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6dbf3de79e51f3d586ab4cb9d5c3e2c14aa28ed23d180cf89b4df0454a69cc87"
 [[package]]
 name = "indexmap"
 version = "2.14.0"
@@ -219,12 +316,37 @@ version = "0.2.186"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "68ab91017fe16c622486840e4c83c9a37afeff978bd239b5293d61ece587de66"
+[[package]]
+name = "libredox"
+version = "0.1.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f02ab6bace2054fb888a3c16f990117b579d14a3088e472d63c6011fa185c9d3"
+dependencies = [
+ "libc",
+]
+[[package]]
+name = "log"
+version = "0.4.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "953f07c43838f8e6f9758cab68bf5bed85465e7587ebe0b823f1bcd81978ad3a"
 [[package]]
 name = "memchr"
 version = "2.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6b947ae49db0d222b1dbc6b113ce7248a3fc3a6ca21b696717bfc000ba4484d8"
+[[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 = "munge"
 version = "0.4.7"
@@ -270,6 +392,18 @@ version = "1.21.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
+[[package]]
+name = "option-ext"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "04744f49eae99ab78e0d5c0b603ab218f515ea8cfe5a456d7629ad883a3b6e7d"
+[[package]]
+name = "percent-encoding"
+version = "2.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b4f627cb1b25917193a259e49bdad08f671f8d9708acfd5fe0a8c1455d87220"
 [[package]]
 name = "pin-project-lite"
 version = "0.2.17"
@@ -414,6 +548,17 @@ dependencies = [
  "crossbeam-utils",
 ]
+[[package]]
+name = "redox_users"
+version = "0.4.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba009ff324d1fc1b900bd1fdb31564febe58a8ccc8a6fdbb93b543d33b13ca43"
+dependencies = [
+ "getrandom 0.2.17",
+ "libredox",
+ "thiserror 1.0.69",
+]
 [[package]]
 name = "ref-cast"
 version = "1.0.25"
@@ -469,6 +614,20 @@ version = "0.5.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cadadef317c2f20755a64d7fdc48f9e7178ee6b0e1f7fce33fa60f1d68a276e6"
+[[package]]
+name = "ring"
+version = "0.17.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a4689e6c2294d81e88dc6261c768b63bc4fcdb852be6d1352498b114f61383b7"
+dependencies = [
+ "cc",
+ "cfg-if",
+ "getrandom 0.2.17",
+ "libc",
+ "untrusted",
+ "windows-sys 0.52.0",
+]
 [[package]]
 name = "rkyv"
 version = "0.8.16"
@@ -498,6 +657,41 @@ dependencies = [
  "syn",
 ]
+[[package]]
+name = "rustls"
+version = "0.23.40"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ef86cd5876211988985292b91c96a8f2d298df24e75989a43a3c73f2d4d8168b"
+dependencies = [
+ "log",
+ "once_cell",
+ "ring",
+ "rustls-pki-types",
+ "rustls-webpki",
+ "subtle",
+ "zeroize",
+]
+[[package]]
+name = "rustls-pki-types"
+version = "1.14.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "30a7197ae7eb376e574fe940d068c30fe0462554a3ddbe4eca7838e049c937a9"
+dependencies = [
+ "zeroize",
+]
+[[package]]
+name = "rustls-webpki"
+version = "0.103.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "61c429a8649f110dddef65e2a5ad240f747e85f7758a6bccc7e5777bd33f756e"
+dependencies = [
+ "ring",
+ "rustls-pki-types",
+ "untrusted",
+]
 [[package]]
 name = "rustversion"
 version = "1.0.22"
@@ -534,6 +728,18 @@ dependencies = [
  "syn",
 ]
+[[package]]
+name = "shlex"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f8fadd59c855ef2080decdef8ff161eb6661b86933c9d82e5ba29dc602a55aba"
+[[package]]
+name = "simd-adler32"
+version = "0.3.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "703d5c7ef118737c72f1af64ad2f6f8c5e1921f818cdcb97b8fe6fc69bf66214"
 [[package]]
 name = "simdutf8"
 version = "0.1.5"
@@ -572,7 +778,7 @@ dependencies = [
  "simdutf8",
  "sonic-number",
  "sonic-simd",
- "thiserror",
+ "thiserror 2.0.18",
  "zmij",
 ]
@@ -585,6 +791,12 @@ dependencies = [
  "cfg-if",
 ]
+[[package]]
+name = "subtle"
+version = "2.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292"
 [[package]]
 name = "syn"
 version = "2.0.117"
@@ -602,13 +814,33 @@ version = "0.13.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "adb6935a6f5c20170eeceb1a3835a49e12e19d792f6dd344ccc76a985ca5a6ca"
+[[package]]
+name = "thiserror"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6aaf5339b578ea85b50e080feb250a3e8ae8cfcdff9a461c9ec2904bc923f52"
+dependencies = [
+ "thiserror-impl 1.0.69",
+]
 [[package]]
 name = "thiserror"
 version = "2.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4288b5bcbc7920c07a1149a35cf9590a2aa808e0bc1eafaade0b80947865fbc4"
 dependencies = [
- "thiserror-impl",
+ "thiserror-impl 2.0.18",
+]
+[[package]]
+name = "thiserror-impl"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
 ]
 [[package]]
@@ -637,12 +869,63 @@ version = "0.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
+[[package]]
+name = "udpipe-rs"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a8f34a036b145a2d253613c2742c836f79c9d5f9c2220f03931762224d23452"
+dependencies = [
+ "cc",
+ "ureq",
+]
 [[package]]
 name = "unicode-ident"
 version = "1.0.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
+[[package]]
+name = "untrusted"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1"
+[[package]]
+name = "ureq"
+version = "3.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dea7109cdcd5864d4eeb1b58a1648dc9bf520360d7af16ec26d0a9354bafcfc0"
+dependencies = [
+ "base64",
+ "flate2",
+ "log",
+ "percent-encoding",
+ "rustls",
+ "rustls-pki-types",
+ "ureq-proto",
+ "utf8-zero",
+ "webpki-roots",
+]
+[[package]]
+name = "ureq-proto"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e994ba84b0bd1b1b0cf92878b7ef898a5c1760108fe7b6010327e274917a808c"
+dependencies = [
+ "base64",
+ "http",
+ "httparse",
+ "log",
+]
+[[package]]
+name = "utf8-zero"
+version = "0.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8c0a043c9540bae7c578c88f91dda8bd82e59ae27c21baca69c8b191aaf5a6e"
 [[package]]
 name = "uuid"
 version = "1.23.2"
@@ -659,6 +942,12 @@ version = "0.9.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
+[[package]]
+name = "wasi"
+version = "0.11.1+wasi-snapshot-preview1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ccf3ec651a847eb01de73ccad15eb7d99f80485de043efb2f370cd654f4ea44b"
 [[package]]
 name = "wasip2"
 version = "1.0.3+wasi-0.2.9"
@@ -713,6 +1002,154 @@ dependencies = [
  "unicode-ident",
 ]
+[[package]]
+name = "webpki-roots"
+version = "1.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "52f5ee44c96cf55f1b349600768e3ece3a8f26010c05265ab73f945bb1a2eb9d"
+dependencies = [
+ "rustls-pki-types",
+]
+[[package]]
+name = "windows-sys"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "677d2418bec65e3338edb076e806bc1ec15693c5d0104683f2efe857f61056a9"
+dependencies = [
+ "windows-targets 0.48.5",
+]
+[[package]]
+name = "windows-sys"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
+dependencies = [
+ "windows-targets 0.52.6",
+]
+[[package]]
+name = "windows-targets"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c"
+dependencies = [
+ "windows_aarch64_gnullvm 0.48.5",
+ "windows_aarch64_msvc 0.48.5",
+ "windows_i686_gnu 0.48.5",
+ "windows_i686_msvc 0.48.5",
+ "windows_x86_64_gnu 0.48.5",
+ "windows_x86_64_gnullvm 0.48.5",
+ "windows_x86_64_msvc 0.48.5",
+]
+[[package]]
+name = "windows-targets"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
+dependencies = [
+ "windows_aarch64_gnullvm 0.52.6",
+ "windows_aarch64_msvc 0.52.6",
+ "windows_i686_gnu 0.52.6",
+ "windows_i686_gnullvm",
+ "windows_i686_msvc 0.52.6",
+ "windows_x86_64_gnu 0.52.6",
+ "windows_x86_64_gnullvm 0.52.6",
+ "windows_x86_64_msvc 0.52.6",
+]
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
+[[package]]
+name = "windows_i686_gnu"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
+[[package]]
+name = "windows_i686_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
+[[package]]
+name = "windows_i686_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
+[[package]]
+name = "windows_i686_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
 [[package]]
 name = "wit-bindgen"
 version = "0.57.1"
@@ -739,6 +1176,12 @@ dependencies = [
  "syn",
 ]
+[[package]]
+name = "zeroize"
+version = "1.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b97154e67e32c85465826e8bcc1c59429aaaf107c1e4a9e53c8d8ccd5eff88d0"
 [[package]]
 name = "zmij"
 version = "1.0.21"

{cc_transcript-0.3.0 → cc_transcript-0.4.0}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cc-transcript
-Version: 0.3.0
+Version: 0.4.0
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: Operating System :: OS Independent
@@ -63,21 +63,24 @@ for event in events:
             print(f"assistant ({model}):", text[:80])
 ```
-`SENTIMENT_FILTER` is a ready-made filter that keeps only user and assistant turns,
-dropping sidechains, synthetic turns, compacted summaries, empty events, and tool/command noise:
+Compose a filter from small building blocks and apply it. The builders return clauses,
+`build_spec` assembles them into a spec, and `apply_spec` yields the survivors:
 ```python
-from cc_transcript import apply_filters, SENTIMENT_FILTER
+from cc_transcript import apply_spec, build_spec, keep_only, drop_junk, drop_short
-clean = list(apply_filters(events, SENTIMENT_FILTER))
+spec = build_spec(keep_only("user", "assistant"), drop_junk("structural"), drop_short(2))
+clean = list(apply_spec(events, spec))
 ```
-Build your own with `FilterConfig` — every rule is off by default, so a bare `FilterConfig()` passes everything through.
+`NOISE_SPEC` is a ready-made spec for the universal structural noise (system reminders,
+local-command output, skill banners). For flag-style filtering, `FilterConfig` is also
+available — every rule is off by default, so a bare `FilterConfig()` passes everything through.
 ## What problems does this solve?
 - **One faithful parse.** Anything reading Claude Code transcripts re-implements the same JSONL quirks (str-or-list content, tool results nested two ways, envelope-less mode markers). This is that parser, written once and typed strictly.
-- **Non-lossy by design.** The event model is a superset: sidechains, `<synthetic>` turns, thinking blocks, and unrecognized entry types all survive parsing. You decide what to drop, via `FilterConfig`.
+- **Non-lossy by design.** The event model is a superset: sidechains, `<synthetic>` turns, thinking blocks, and unrecognized entry types all survive parsing. You decide what to drop, via composable filter specs (`build_spec`) or `FilterConfig`.
 - **Incremental ingestion.** `FileStateStore` tracks per-file mtimes in SQLite (WAL, thread-safe) so re-runs only reparse changed files, and you compose your own writes in the same transaction.
 - **Pluggable backends.** A Rust backend (PyO3 + rayon) is the default fast path, with a pure-Python reference parser behind the same `Backend` protocol as the fallback — both at full event parity.

{cc_transcript-0.3.0 → cc_transcript-0.4.0}/README.md RENAMED Viewed

@@ -32,21 +32,24 @@ for event in events:
             print(f"assistant ({model}):", text[:80])
 ```
-`SENTIMENT_FILTER` is a ready-made filter that keeps only user and assistant turns,
-dropping sidechains, synthetic turns, compacted summaries, empty events, and tool/command noise:
+Compose a filter from small building blocks and apply it. The builders return clauses,
+`build_spec` assembles them into a spec, and `apply_spec` yields the survivors:
 ```python
-from cc_transcript import apply_filters, SENTIMENT_FILTER
+from cc_transcript import apply_spec, build_spec, keep_only, drop_junk, drop_short
-clean = list(apply_filters(events, SENTIMENT_FILTER))
+spec = build_spec(keep_only("user", "assistant"), drop_junk("structural"), drop_short(2))
+clean = list(apply_spec(events, spec))
 ```
-Build your own with `FilterConfig` — every rule is off by default, so a bare `FilterConfig()` passes everything through.
+`NOISE_SPEC` is a ready-made spec for the universal structural noise (system reminders,
+local-command output, skill banners). For flag-style filtering, `FilterConfig` is also
+available — every rule is off by default, so a bare `FilterConfig()` passes everything through.
 ## What problems does this solve?
 - **One faithful parse.** Anything reading Claude Code transcripts re-implements the same JSONL quirks (str-or-list content, tool results nested two ways, envelope-less mode markers). This is that parser, written once and typed strictly.
-- **Non-lossy by design.** The event model is a superset: sidechains, `<synthetic>` turns, thinking blocks, and unrecognized entry types all survive parsing. You decide what to drop, via `FilterConfig`.
+- **Non-lossy by design.** The event model is a superset: sidechains, `<synthetic>` turns, thinking blocks, and unrecognized entry types all survive parsing. You decide what to drop, via composable filter specs (`build_spec`) or `FilterConfig`.
 - **Incremental ingestion.** `FileStateStore` tracks per-file mtimes in SQLite (WAL, thread-safe) so re-runs only reparse changed files, and you compose your own writes in the same transaction.
 - **Pluggable backends.** A Rust backend (PyO3 + rayon) is the default fast path, with a pure-Python reference parser behind the same `Backend` protocol as the fallback — both at full event parity.

cc-transcript 0.3.0__tar.gz → 0.4.0__tar.gz

cc-transcript 0.3.0tar.gz → 0.4.0tar.gz