headson 0.2.4__tar.gz → 0.3.0__tar.gz

{headson-0.2.4 → headson-0.3.0}/Cargo.lock

@@ -2,18 +2,6 @@
 # It is not intended for manual editing.
 version = 4
 
-[[package]]
-name = "ahash"
-version = "0.8.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
-dependencies = [
- "cfg-if",
- "once_cell",
- "version_check",
- "zerocopy",
-]
-
 [[package]]
 name = "allocator-api2"
 version = "0.2.21"
@@ -115,12 +103,6 @@ dependencies = [
  "serde",
 ]
 
-[[package]]
-name = "bumpalo"
-version = "3.19.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "46c5e41b57b8bba42a04676d81cb89e9ee8e859a1a66f80a5a72e1cb76b34d43"
-
 [[package]]
 name = "cfg-if"
 version = "1.0.4"
@@ -194,12 +176,6 @@ dependencies = [
  "memchr",
 ]
 
-[[package]]
-name = "deunicode"
-version = "1.6.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "abd57806937c9cc163efc8ea3910e00a62e2aeb0b8119f1793a978088f8f6b04"
-
 [[package]]
 name = "difflib"
 version = "0.4.0"
@@ -218,6 +194,12 @@ version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "34aa73646ffb006b8f5147f3dc182bd4bcb190227ce861fc4a4844bf8e3cb2c0"
 
+[[package]]
+name = "equivalent"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f"
+
 [[package]]
 name = "errno"
 version = "0.3.14"
@@ -228,16 +210,6 @@ dependencies = [
  "windows-sys 0.60.2",
 ]
 
-[[package]]
-name = "fake"
-version = "2.10.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2d391ba4af7f1d93f01fcf7b2f29e2bc9348e109dfdbf4dcbdc51dfa38dab0b6"
-dependencies = [
- "deunicode",
- "rand",
-]
-
 [[package]]
 name = "fastrand"
 version = "2.3.0"
@@ -246,25 +218,18 @@ checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
 
 [[package]]
 name = "float-cmp"
-version = "0.9.0"
+version = "0.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "98de4bbd547a563b716d8dfa9aad1cb19bfab00f4fa09a6a4ed21dbcf44ce9c4"
+checksum = "b09cf3155332e944990140d967ff5eceb70df778b34f77d8075db46e4704e6d8"
 dependencies = [
  "num-traits",
 ]
 
 [[package]]
-name = "getrandom"
-version = "0.2.16"
+name = "foldhash"
+version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "335ff9f135e4384c8150d6f27c6daed433577f86b4750418338c01a1a2528592"
-dependencies = [
- "cfg-if",
- "js-sys",
- "libc",
- "wasi",
- "wasm-bindgen",
-]
+checksum = "77ce24cb58228fbb8aa041425bb1050850ac19177686ea6e0f41a70416f56fdb"
 
 [[package]]
 name = "getrandom"
@@ -280,9 +245,9 @@ dependencies = [
 
 [[package]]
 name = "halfbrown"
-version = "0.2.5"
+version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8588661a8607108a5ca69cab034063441a0413a0b041c13618a7dd348021ef6f"
+checksum = "0c7ed2f2edad8a14c8186b847909a41fbb9c3eafa44f88bd891114ed5019da09"
 dependencies = [
  "hashbrown",
  "serde",
@@ -290,23 +255,23 @@ dependencies = [
 
 [[package]]
 name = "hashbrown"
-version = "0.14.5"
+version = "0.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e5274423e17b7c9fc20b6e7e208532f9b19825d82dfd615708b70edd83df41f1"
+checksum = "5419bdc4f6a9207fbeba6d11b604d481addf78ecd10c11ad51e76c2f6482748d"
 dependencies = [
- "ahash",
  "allocator-api2",
+ "equivalent",
+ "foldhash",
 ]
 
 [[package]]
 name = "headson"
-version = "0.2.4"
+version = "0.3.0"
 dependencies = [
  "anyhow",
  "assert_cmd",
  "clap",
  "content_inspector",
- "fake",
  "insta",
  "rand",
  "rand_chacha",
@@ -347,73 +312,6 @@ version = "1.0.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4a5f13b858c8d314ee3e8f639011f7ccefe71f97f96e50151fb991f267928e2c"
 
-[[package]]
-name = "js-sys"
-version = "0.3.81"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec48937a97411dcb524a265206ccd4c90bb711fca92b2792c407f268825b9305"
-dependencies = [
- "once_cell",
- "wasm-bindgen",
-]
-
-[[package]]
-name = "lexical-core"
-version = "1.0.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7d8d125a277f807e55a77304455eb7b1cb52f2b18c143b60e766c120bd64a594"
-dependencies = [
- "lexical-parse-float",
- "lexical-parse-integer",
- "lexical-util",
- "lexical-write-float",
- "lexical-write-integer",
-]
-
-[[package]]
-name = "lexical-parse-float"
-version = "1.0.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "52a9f232fbd6f550bc0137dcb5f99ab674071ac2d690ac69704593cb4abbea56"
-dependencies = [
- "lexical-parse-integer",
- "lexical-util",
-]
-
-[[package]]
-name = "lexical-parse-integer"
-version = "1.0.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9a7a039f8fb9c19c996cd7b2fcce303c1b2874fe1aca544edc85c4a5f8489b34"
-dependencies = [
- "lexical-util",
-]
-
-[[package]]
-name = "lexical-util"
-version = "1.0.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2604dd126bb14f13fb5d1bd6a66155079cb9fa655b37f875b3a742c705dbed17"
-
-[[package]]
-name = "lexical-write-float"
-version = "1.0.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "50c438c87c013188d415fbabbb1dceb44249ab81664efbd31b14ae55dabb6361"
-dependencies = [
- "lexical-util",
- "lexical-write-integer",
-]
-
-[[package]]
-name = "lexical-write-integer"
-version = "1.0.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "409851a618475d2d5796377cad353802345cba92c867d9fbcde9cf4eac4e14df"
-dependencies = [
- "lexical-util",
-]
-
 [[package]]
 name = "libc"
 version = "0.2.177"
@@ -426,12 +324,6 @@ version = "0.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "df1d3c3b53da64cf5760482273a98e575c651a67eec7f77df96b5b642de8f039"
 
-[[package]]
-name = "log"
-version = "0.4.28"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "34080505efa8e45a4b816c349525ebe327ceaa8559756f0356cba97ef3bf7432"
-
 [[package]]
 name = "memchr"
 version = "2.7.6"
@@ -521,20 +413,19 @@ checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
 
 [[package]]
 name = "rand"
-version = "0.8.5"
+version = "0.9.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
+checksum = "6db2770f06117d490610c7488547d543617b21bfa07796d7a12f6f1bd53850d1"
 dependencies = [
- "libc",
  "rand_chacha",
  "rand_core",
 ]
 
 [[package]]
 name = "rand_chacha"
-version = "0.3.1"
+version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88"
+checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
 dependencies = [
  "ppv-lite86",
  "rand_core",
@@ -542,11 +433,11 @@ dependencies = [
 
 [[package]]
 name = "rand_core"
-version = "0.6.4"
+version = "0.9.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
+checksum = "99d9a13982dcf210057a8a78572b2217b667c3beacbf3a0d8b454f6f82837d38"
 dependencies = [
- "getrandom 0.2.16",
+ "getrandom",
 ]
 
 [[package]]
@@ -588,12 +479,6 @@ dependencies = [
  "windows-sys 0.60.2",
 ]
 
-[[package]]
-name = "rustversion"
-version = "1.0.22"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
-
 [[package]]
 name = "ryu"
 version = "1.0.20"
@@ -645,13 +530,11 @@ dependencies = [
 
 [[package]]
 name = "simd-json"
-version = "0.13.11"
+version = "0.17.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a0228a564470f81724e30996bbc2b171713b37b15254a6440c7e2d5449b95691"
+checksum = "4255126f310d2ba20048db6321c81ab376f6a6735608bf11f0785c41f01f64e3"
 dependencies = [
- "getrandom 0.2.16",
  "halfbrown",
- "lexical-core",
  "ref-cast",
  "serde",
  "serde_json",
@@ -695,7 +578,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2d31c77bdf42a745371d260a26ca7163f1e0924b64afa0b688e61b5a9fa02f16"
 dependencies = [
  "fastrand",
- "getrandom 0.3.4",
+ "getrandom",
  "once_cell",
  "rustix",
  "windows-sys 0.60.2",
@@ -739,9 +622,9 @@ checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
 
 [[package]]
 name = "value-trait"
-version = "0.8.1"
+version = "0.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dad8db98c1e677797df21ba03fca7d3bf9bec3ca38db930954e4fe6e1ea27eb4"
+checksum = "8e80f0c733af0720a501b3905d22e2f97662d8eacfe082a75ed7ffb5ab08cb59"
 dependencies = [
  "float-cmp",
  "halfbrown",
@@ -749,12 +632,6 @@ dependencies = [
  "ryu",
 ]
 
-[[package]]
-name = "version_check"
-version = "0.9.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
-
 [[package]]
 name = "wait-timeout"
 version = "0.2.1"
@@ -764,12 +641,6 @@ dependencies = [
  "libc",
 ]
 
-[[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 = "1.0.1+wasi-0.2.4"
@@ -779,65 +650,6 @@ dependencies = [
  "wit-bindgen",
 ]
 
-[[package]]
-name = "wasm-bindgen"
-version = "0.2.104"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c1da10c01ae9f1ae40cbfac0bac3b1e724b320abfcf52229f80b547c0d250e2d"
-dependencies = [
- "cfg-if",
- "once_cell",
- "rustversion",
- "wasm-bindgen-macro",
- "wasm-bindgen-shared",
-]
-
-[[package]]
-name = "wasm-bindgen-backend"
-version = "0.2.104"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "671c9a5a66f49d8a47345ab942e2cb93c7d1d0339065d4f8139c486121b43b19"
-dependencies = [
- "bumpalo",
- "log",
- "proc-macro2",
- "quote",
- "syn",
- "wasm-bindgen-shared",
-]
-
-[[package]]
-name = "wasm-bindgen-macro"
-version = "0.2.104"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7ca60477e4c59f5f2986c50191cd972e3a50d8a95603bc9434501cf156a9a119"
-dependencies = [
- "quote",
- "wasm-bindgen-macro-support",
-]
-
-[[package]]
-name = "wasm-bindgen-macro-support"
-version = "0.2.104"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9f07d2f20d4da7b26400c9f4a0511e6e0345b040694e8a75bd41d578fa4421d7"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
- "wasm-bindgen-backend",
- "wasm-bindgen-shared",
-]
-
-[[package]]
-name = "wasm-bindgen-shared"
-version = "0.2.104"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bad67dc8b2a1a6e5448428adec4c3e84c43e561d8c9ee8a9e5aabeb193ec41d1"
-dependencies = [
- "unicode-ident",
-]
-
 [[package]]
 name = "windows-link"
 version = "0.2.1"

{headson-0.2.4 → headson-0.3.0}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "headson"
-version = "0.2.4"
+version = "0.3.0"
 edition = "2024"
 description = "Budget‑constrained JSON preview renderer"
 readme = "README.md"
@@ -24,16 +24,15 @@ clap = { version = "4.5.49", features = ["derive"] }
 serde = { version = "1.0.228", features = ["derive"] }
 serde_json = "1.0.145"
 unicode-segmentation = "1.12.0"
-simd-json = { version = "0.13", features = ["serde_impl"] }
+simd-json = { version = "0.17", features = ["serde_impl"] }
 content_inspector = "0.2"
 
 [dev-dependencies]
 insta = "1.40.0"
 assert_cmd = "2"
 test_each_file = "0.3"
-fake = "2"
-rand = "0.8"
-rand_chacha = "0.3"
+rand = "0.9"
+rand_chacha = "0.9"
 tempfile = "3"
 
 [profile.release]
@@ -94,3 +93,6 @@ implicit_hasher = "deny"
 uninlined_format_args = "deny"
 float_cmp = "deny"
 float_cmp_const = "deny"
+
+[lints.rust]
+dead_code = "warn"

headson-0.3.0/PKG-INFO

@@ -0,0 +1,168 @@
+Metadata-Version: 2.4
+Name: headson
+Version: 0.3.0
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Rust
+Classifier: Operating System :: OS Independent
+Requires-Dist: pytest>=8 ; extra == 'test'
+Provides-Extra: test
+License-File: LICENSE
+Summary: Budget‑constrained JSON preview renderer (Python bindings)
+Keywords: json,preview,summarize,cli,bindings
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
+
+# headson
+
+Head/tail for JSON — but structure‑aware. Get a compact preview that shows both the shape and representative values of your data, all within a strict character budget.
+
+Available as:
+- CLI (see [Usage](#usage))
+- Python library (see [Python Bindings](#python-bindings))
+
+## Install
+
+Using Cargo:
+
+    cargo install headson
+
+From source:
+
+    cargo build --release
+    target/release/headson --help
+
+
+## Features
+
+- *Budgeted output*: specify exactly how much JSON you want to see
+- *Multiple output formats* : `json` (machine‑readable), `pseudo` (human‑friendly), `js` (valid JavaScript, most detailed metadata).
+- *Multiple inputs*: preview many files at once with a shared or per‑file budget.
+- *Fast*: can process gigabyte-scale files in seconds (mostly disk-constrained)
+- *Available as a CLI app and as a Python library*
+
+## Fits into command line workflows
+
+If you’re comfortable with tools like `head` and `tail`, use `headson` when you want a quick, structured peek into a JSON file without dumping the entire thing.
+
+- `head`/`tail` operate on bytes/lines - their output is not optimized for tree structures
+- `jq` you need to craft filters to preview large JSON files
+- `headson` is like head/tail for trees: zero config but it keeps structure and represents content as much as possible 
+
+## Usage
+
+    headson [FLAGS] [INPUT...]
+
+- INPUT (optional, repeatable): file path(s). If omitted, reads JSON from stdin. Multiple input files are supported.
+- Prints the preview to stdout. On parse errors, exits non‑zero and prints an error to stderr.
+
+Common flags:
+
+- `-n, --budget <BYTES>`: per‑file output budget. When multiple input files are provided, the total budget equals `<BYTES> * number_of_inputs`.
+- `-N, --global-budget <BYTES>`: total output budget across all inputs. Useful when you want a fixed-size preview across many files (may omit entire files). Mutually exclusive with `--budget`.
+- `-f, --template <json|pseudo|js>`: output style (default: `pseudo`)
+- `-m, --compact`: no indentation, no spaces, no newlines
+- `--no-newline`: single line output
+- `--no-space`: no space after `:` in objects
+- `--indent <STR>`: indentation unit (default: two spaces)
+- `--string-cap <N>`: max graphemes to consider per string (default: 500)
+- `--tail`: prefer the end of arrays when truncating. Strings are unaffected. In `pseudo`/`js` templates the omission marker appears at the start; `json` remains strict JSON with no annotations.
+
+Notes:
+
+- With multiple input files:
+  - JSON template outputs a single JSON object keyed by the input file paths.
+  - Pseudo and JS templates render file sections with human-readable headers.
+  - Using `--global-budget` may truncate or omit entire files to respect the total budget.
+  - The tool finds the largest preview that fits the budget; if even the tiniest preview exceeds it, you still get a minimal, valid preview.
+  - When passing file paths, directories and binary files are ignored; a notice is printed to stderr for each (e.g., `Ignored binary file: ./path/to/file`). Stdin mode reads the stream as-is.
+
+Quick one‑liners:
+
+- Peek a big JSON stream (keeps structure):
+
+      zstdcat huge.json.zst | headson -n 800 -f pseudo
+
+- Many files with a fixed overall size:
+
+      headson -N 1200 -f json logs/*.json
+
+- Glance at a file, JavaScript‑style comments for omissions:
+
+      headson -n 400 -f js data.json
+
+Show help:
+
+    headson --help
+
+## Examples: head vs headson
+
+Input:
+
+```json
+{"users":[{"id":1,"name":"Ana","roles":["admin","dev"]},{"id":2,"name":"Bo"}],"meta":{"count":2,"source":"db"}}
+```
+
+Naive cut (can break mid‑token):
+
+```bash
+jq -c . users.json | head -c 80
+# {"users":[{"id":1,"name":"Ana","roles":["admin","dev"]},{"id":2,"name":"Bo"}],"me
+```
+
+Structured preview with headson (pseudo):
+
+```bash
+headson -n 120 -f pseudo users.json
+# {
+#   users: [
+#     { id: 1, name: "Ana", roles: [ "admin", … ] },
+#     …
+#   ]
+#   meta: { count: 2, … }
+# }
+```
+
+Machine‑readable preview (json):
+
+```bash
+headson -n 120 -f json users.json
+# {"users":[{"id":1,"name":"Ana","roles":["admin"]}],"meta":{"count":2}}
+```
+
+## Python Bindings
+
+A thin Python extension module is available on PyPI as `headson`.
+
+- Install: `pip install headson` (prebuilt wheels for CPython 3.10–3.12 on Linux/macOS/Windows). Older/newer Python versions may build from source if Rust is installed.
+- API:
+  - `headson.summarize(text: str, *, template: str = "pseudo", character_budget: int | None = None, tail: bool = False) -> str`
+    - `template`: one of `"json" | "pseudo" | "js"`
+    - `character_budget`: maximum output size in characters (default: 500)
+    - `tail`: prefer the end of arrays when truncating; strings unaffected. Affects only display templates (`pseudo`/`js`); `json` remains strict.
+
+Example:
+
+```python
+import json
+import headson
+
+data = {"foo": [1, 2, 3], "bar": {"x": "y"}}
+preview = headson.summarize(json.dumps(data), template="json", character_budget=200)
+print(preview)
+
+# Prefer the tail of arrays (annotations show in pseudo/js only)
+print(
+    headson.summarize(
+        json.dumps(list(range(100))),
+        template="pseudo",
+        character_budget=80,
+        tail=True,
+    )
+)
+```
+
+## License
+
+MIT
+