headson 0.6.3__tar.gz → 0.6.5__tar.gz

{headson-0.6.3 → headson-0.6.5}/Cargo.lock

@@ -298,7 +298,7 @@ dependencies = [
 
 [[package]]
 name = "headson"
-version = "0.6.3"
+version = "0.6.5"
 dependencies = [
  "anyhow",
  "assert_cmd",

{headson-0.6.3 → headson-0.6.5}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "headson"
-version = "0.6.3"
+version = "0.6.5"
 edition = "2024"
 description = "Budget‑constrained JSON preview renderer"
 readme = "README.md"

{headson-0.6.3 → headson-0.6.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: headson
-Version: 0.6.3
+Version: 0.6.5
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Rust
@@ -20,12 +20,15 @@ Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
   <br/>
 </p>
 
-`heal`/`tail` for JSON, YAML - but structure‑aware. Get a compact preview that shows both the shape and representative values of your data, all within a strict character budget. (Just like `head`/`tail`, `headson` can also work with unstructured text files.)
+`heal`/`tail` for JSON, YAML - but structure‑aware. Get a compact preview that shows both the shape and representative values of your data, all within a strict byte budget. (Just like `head`/`tail`, `headson` can also work with unstructured text files.)
 
 Available as:
 - CLI (see [Usage](#usage))
 - Python library (see [Python Bindings](#python-bindings))
 
+![Codecov](https://img.shields.io/codecov/c/github/kantord/headson?style=flat-square) ![Crates.io Version](https://img.shields.io/crates/v/headson?style=flat-square) ![PyPI - Version](https://img.shields.io/pypi/v/headson?style=flat-square)
+
+
 ## Install
 
 Using Cargo:
@@ -67,8 +70,8 @@ If you’re comfortable with tools like `head` and `tail`, use `headson` when yo
 
 Common flags:
 
-- `-n, --budget <BYTES>`: per‑file output budget. For multiple inputs, default total budget is `<BYTES> * number_of_inputs`.
-- `-N, --global-budget <BYTES>`: total output budget across all inputs. With `--budget`, the effective total is the smaller of the two.
+- `-c, --bytes <BYTES>`: per‑file output budget. For multiple inputs, default total budget is `<BYTES> * number_of_inputs`.
+- `-C, --global-bytes <BYTES>`: total output budget across all inputs. With `--bytes`, the effective total is the smaller of the two.
 - `-f, --format <auto|json|yaml|text>`: output format (default: `auto`).
   - Auto: stdin → JSON family; filesets → per‑file based on extension (`.json` → JSON family, `.yaml`/`.yml` → YAML, unknown → Text).
 - `-t, --template <strict|default|detailed>`: output style (default: `default`).
@@ -89,7 +92,7 @@ Notes:
   - With newlines enabled, file sections are rendered with human‑readable headers. In compact/single‑line modes, headers are omitted.
 - In `--format auto`, each file uses its own best format: JSON family for `.json`, YAML for `.yaml`/`.yml`.
   - Unknown extensions are treated as Text (raw lines) — safe for logs and `.txt` files.
-  - `--global-budget` may truncate or omit entire files to respect the total budget.
+  - `--global-bytes` may truncate or omit entire files to respect the total budget.
   - The tool finds the largest preview that fits the budget; even if extremely tight, you still get a minimal, valid preview.
   - Directories and binary files are ignored; a notice is printed to stderr for each. Stdin reads the stream as‑is.
   - Head vs Tail sampling: these options bias which part of arrays are kept before rendering. Display styles may still insert internal gap markers to honor very small budgets; strict JSON stays unannotated.
@@ -98,33 +101,33 @@ Quick one‑liners:
 
 - Peek a big JSON stream (keeps structure):
 
-      zstdcat huge.json.zst | headson -n 800 -f json -t default
+      zstdcat huge.json.zst | headson -c 800 -f json -t default
 
 - Many files with a fixed overall size:
 
-      headson -N 1200 -f json -t strict logs/*.json
+      headson -C 1200 -f json -t strict logs/*.json
 
 - Glance at a file, JavaScript‑style comments for omissions:
 
-      headson -n 400 -f json -t detailed data.json
+      headson -c 400 -f json -t detailed data.json
 
 - YAML with detailed comments:
 
-      headson -n 400 -f yaml -t detailed config.yaml
+      headson -c 400 -f yaml -t detailed config.yaml
 
 ### Text mode
 
 - Single file (auto):
 
-      headson -n 200 notes.txt
+      headson -c 200 notes.txt
 
 - Force Text ingest/output (useful when mixing with other extensions):
 
-      headson -n 200 -i text -f text notes.txt
+      headson -c 200 -i text -f text notes.txt
 
 - Many text files (fileset):
 
-      headson -n 800 -i text -f text logs/*.txt
+      headson -c 800 -i text -f text logs/*.txt
 
 - Styles on Text:
   - default: omission as a standalone `…` line.
@@ -135,6 +138,8 @@ Show help:
 
     headson --help
 
+Note: flags align with head/tail conventions (`-c/--bytes`, `-C/--global-bytes`).
+
 ## Examples: head vs headson
 
 Input:
@@ -153,7 +158,7 @@ jq -c . users.json | head -c 80
 Structured preview with headson (JSON family, default style → Pseudo):
 
 ```bash
-headson -n 120 -f json -t default users.json
+headson -c 120 -f json -t default users.json
 # {
 #   users: [
 #     { id: 1, name: "Ana", roles: [ "admin", … ] },
@@ -166,7 +171,7 @@ headson -n 120 -f json -t default users.json
 Machine‑readable preview (JSON family, strict style → strict JSON):
 
 ```bash
-headson -n 120 -f json -t strict users.json
+headson -c 120 -f json -t strict users.json
 # {"users":[{"id":1,"name":"Ana","roles":["admin"]}],"meta":{"count":2}}
 ```
 
@@ -185,11 +190,11 @@ A thin Python extension module is available on PyPI as `headson`.
 
 - Install: `pip install headson` (ABI3 wheels for Python 3.10+ on Linux/macOS/Windows).
 - API:
-  - `headson.summarize(text: str, *, format: str = "auto", style: str = "default", input_format: str = "json", character_budget: int | None = None, skew: str = "balanced") -> str`
+  - `headson.summarize(text: str, *, format: str = "auto", style: str = "default", input_format: str = "json", byte_budget: int | None = None, skew: str = "balanced") -> str`
     - `format`: `"auto" | "json" | "yaml"` (auto maps to JSON family for single inputs)
     - `style`: `"strict" | "default" | "detailed"`
     - `input_format`: `"json" | "yaml"` (ingestion)
-    - `character_budget`: maximum output size in characters (default: 500)
+    - `byte_budget`: maximum output size in bytes (default: 500)
     - `skew`: `"balanced" | "head" | "tail"` (affects display styles; strict JSON remains unannotated)
 
 Examples:
@@ -199,7 +204,7 @@ import json
 import headson
 
 data = {"foo": [1, 2, 3], "bar": {"x": "y"}}
-preview = headson.summarize(json.dumps(data), format="json", style="strict", character_budget=200)
+preview = headson.summarize(json.dumps(data), format="json", style="strict", byte_budget=200)
 print(preview)
 
 # Prefer the tail of arrays (annotations show with style="default"/"detailed")
@@ -208,14 +213,14 @@ print(
         json.dumps(list(range(100))),
         format="json",
         style="detailed",
-        character_budget=80,
+        byte_budget=80,
         skew="tail",
     )
 )
 
 # YAML support
 doc = "root:\n  items: [1,2,3,4,5,6,7,8,9,10]\n"
-print(headson.summarize(doc, format="yaml", style="default", input_format="yaml", character_budget=60))
+print(headson.summarize(doc, format="yaml", style="default", input_format="yaml", byte_budget=60))
 ```
 
 # Algorithm
@@ -225,7 +230,7 @@ print(headson.summarize(doc, format="yaml", style="default", input_format="yaml"
 ## Footnotes
  - <sup><b>[1]</b></sup> <b>Optimized tree representation</b>: An arena‑style tree stored in flat, contiguous buffers. Each node records its kind and value plus index ranges into shared child and key arrays. Arrays are ingested in a single pass and may be deterministically pre‑sampled: the first element is always kept; additional elements are selected via a fixed per‑index inclusion test; for kept elements, original indices are stored and full lengths are counted. This enables accurate omission info and internal gap markers later, while minimizing pointer chasing.
  - <sup><b>[2]</b></sup> <b>Priority order</b>: Nodes are scored so previews surface representative structure and values first. Arrays can favor head/mid/tail coverage (default) or strictly the head; tail preference flips head/tail when configured. Object properties are ordered by key, and strings expand by grapheme with early characters prioritized over very deep expansions.
- - <sup><b>[3]</b></sup> <b>Choose top N nodes (binary search)</b>: Iteratively picks N so that the rendered preview fits within the character budget, looping between “choose N” and a render attempt to converge quickly.
+ - <sup><b>[3]</b></sup> <b>Choose top N nodes (binary search)</b>: Iteratively picks N so that the rendered preview fits within the byte budget, looping between “choose N” and a render attempt to converge quickly.
  - <sup><b>[4]</b></sup> <b>Render attempt</b>: Serializes the currently included nodes using the selected template. Omission summaries and per-file section headers appear in display templates (pseudo/js); json remains strict. For arrays, display templates may insert internal gap markers between non‑contiguous kept items using original indices.
  - <sup><b>[5]</b></sup> <b>Diagram source</b>: The Algorithm diagram is generated from `docs/diagrams/algorithm.mmd`. Regenerate the SVG with `cargo make diagrams` before releasing.
 

{headson-0.6.3 → headson-0.6.5}/README.md

@@ -6,12 +6,15 @@
   <br/>
 </p>
 
-`heal`/`tail` for JSON, YAML - but structure‑aware. Get a compact preview that shows both the shape and representative values of your data, all within a strict character budget. (Just like `head`/`tail`, `headson` can also work with unstructured text files.)
+`heal`/`tail` for JSON, YAML - but structure‑aware. Get a compact preview that shows both the shape and representative values of your data, all within a strict byte budget. (Just like `head`/`tail`, `headson` can also work with unstructured text files.)
 
 Available as:
 - CLI (see [Usage](#usage))
 - Python library (see [Python Bindings](#python-bindings))
 
+![Codecov](https://img.shields.io/codecov/c/github/kantord/headson?style=flat-square) ![Crates.io Version](https://img.shields.io/crates/v/headson?style=flat-square) ![PyPI - Version](https://img.shields.io/pypi/v/headson?style=flat-square)
+
+
 ## Install
 
 Using Cargo:
@@ -53,8 +56,8 @@ If you’re comfortable with tools like `head` and `tail`, use `headson` when yo
 
 Common flags:
 
-- `-n, --budget <BYTES>`: per‑file output budget. For multiple inputs, default total budget is `<BYTES> * number_of_inputs`.
-- `-N, --global-budget <BYTES>`: total output budget across all inputs. With `--budget`, the effective total is the smaller of the two.
+- `-c, --bytes <BYTES>`: per‑file output budget. For multiple inputs, default total budget is `<BYTES> * number_of_inputs`.
+- `-C, --global-bytes <BYTES>`: total output budget across all inputs. With `--bytes`, the effective total is the smaller of the two.
 - `-f, --format <auto|json|yaml|text>`: output format (default: `auto`).
   - Auto: stdin → JSON family; filesets → per‑file based on extension (`.json` → JSON family, `.yaml`/`.yml` → YAML, unknown → Text).
 - `-t, --template <strict|default|detailed>`: output style (default: `default`).
@@ -75,7 +78,7 @@ Notes:
   - With newlines enabled, file sections are rendered with human‑readable headers. In compact/single‑line modes, headers are omitted.
 - In `--format auto`, each file uses its own best format: JSON family for `.json`, YAML for `.yaml`/`.yml`.
   - Unknown extensions are treated as Text (raw lines) — safe for logs and `.txt` files.
-  - `--global-budget` may truncate or omit entire files to respect the total budget.
+  - `--global-bytes` may truncate or omit entire files to respect the total budget.
   - The tool finds the largest preview that fits the budget; even if extremely tight, you still get a minimal, valid preview.
   - Directories and binary files are ignored; a notice is printed to stderr for each. Stdin reads the stream as‑is.
   - Head vs Tail sampling: these options bias which part of arrays are kept before rendering. Display styles may still insert internal gap markers to honor very small budgets; strict JSON stays unannotated.
@@ -84,33 +87,33 @@ Quick one‑liners:
 
 - Peek a big JSON stream (keeps structure):
 
-      zstdcat huge.json.zst | headson -n 800 -f json -t default
+      zstdcat huge.json.zst | headson -c 800 -f json -t default
 
 - Many files with a fixed overall size:
 
-      headson -N 1200 -f json -t strict logs/*.json
+      headson -C 1200 -f json -t strict logs/*.json
 
 - Glance at a file, JavaScript‑style comments for omissions:
 
-      headson -n 400 -f json -t detailed data.json
+      headson -c 400 -f json -t detailed data.json
 
 - YAML with detailed comments:
 
-      headson -n 400 -f yaml -t detailed config.yaml
+      headson -c 400 -f yaml -t detailed config.yaml
 
 ### Text mode
 
 - Single file (auto):
 
-      headson -n 200 notes.txt
+      headson -c 200 notes.txt
 
 - Force Text ingest/output (useful when mixing with other extensions):
 
-      headson -n 200 -i text -f text notes.txt
+      headson -c 200 -i text -f text notes.txt
 
 - Many text files (fileset):
 
-      headson -n 800 -i text -f text logs/*.txt
+      headson -c 800 -i text -f text logs/*.txt
 
 - Styles on Text:
   - default: omission as a standalone `…` line.
@@ -121,6 +124,8 @@ Show help:
 
     headson --help
 
+Note: flags align with head/tail conventions (`-c/--bytes`, `-C/--global-bytes`).
+
 ## Examples: head vs headson
 
 Input:
@@ -139,7 +144,7 @@ jq -c . users.json | head -c 80
 Structured preview with headson (JSON family, default style → Pseudo):
 
 ```bash
-headson -n 120 -f json -t default users.json
+headson -c 120 -f json -t default users.json
 # {
 #   users: [
 #     { id: 1, name: "Ana", roles: [ "admin", … ] },
@@ -152,7 +157,7 @@ headson -n 120 -f json -t default users.json
 Machine‑readable preview (JSON family, strict style → strict JSON):
 
 ```bash
-headson -n 120 -f json -t strict users.json
+headson -c 120 -f json -t strict users.json
 # {"users":[{"id":1,"name":"Ana","roles":["admin"]}],"meta":{"count":2}}
 ```
 
@@ -171,11 +176,11 @@ A thin Python extension module is available on PyPI as `headson`.
 
 - Install: `pip install headson` (ABI3 wheels for Python 3.10+ on Linux/macOS/Windows).
 - API:
-  - `headson.summarize(text: str, *, format: str = "auto", style: str = "default", input_format: str = "json", character_budget: int | None = None, skew: str = "balanced") -> str`
+  - `headson.summarize(text: str, *, format: str = "auto", style: str = "default", input_format: str = "json", byte_budget: int | None = None, skew: str = "balanced") -> str`
     - `format`: `"auto" | "json" | "yaml"` (auto maps to JSON family for single inputs)
     - `style`: `"strict" | "default" | "detailed"`
     - `input_format`: `"json" | "yaml"` (ingestion)
-    - `character_budget`: maximum output size in characters (default: 500)
+    - `byte_budget`: maximum output size in bytes (default: 500)
     - `skew`: `"balanced" | "head" | "tail"` (affects display styles; strict JSON remains unannotated)
 
 Examples:
@@ -185,7 +190,7 @@ import json
 import headson
 
 data = {"foo": [1, 2, 3], "bar": {"x": "y"}}
-preview = headson.summarize(json.dumps(data), format="json", style="strict", character_budget=200)
+preview = headson.summarize(json.dumps(data), format="json", style="strict", byte_budget=200)
 print(preview)
 
 # Prefer the tail of arrays (annotations show with style="default"/"detailed")
@@ -194,14 +199,14 @@ print(
         json.dumps(list(range(100))),
         format="json",
         style="detailed",
-        character_budget=80,
+        byte_budget=80,
         skew="tail",
     )
 )
 
 # YAML support
 doc = "root:\n  items: [1,2,3,4,5,6,7,8,9,10]\n"
-print(headson.summarize(doc, format="yaml", style="default", input_format="yaml", character_budget=60))
+print(headson.summarize(doc, format="yaml", style="default", input_format="yaml", byte_budget=60))
 ```
 
 # Algorithm
@@ -211,7 +216,7 @@ print(headson.summarize(doc, format="yaml", style="default", input_format="yaml"
 ## Footnotes
  - <sup><b>[1]</b></sup> <b>Optimized tree representation</b>: An arena‑style tree stored in flat, contiguous buffers. Each node records its kind and value plus index ranges into shared child and key arrays. Arrays are ingested in a single pass and may be deterministically pre‑sampled: the first element is always kept; additional elements are selected via a fixed per‑index inclusion test; for kept elements, original indices are stored and full lengths are counted. This enables accurate omission info and internal gap markers later, while minimizing pointer chasing.
  - <sup><b>[2]</b></sup> <b>Priority order</b>: Nodes are scored so previews surface representative structure and values first. Arrays can favor head/mid/tail coverage (default) or strictly the head; tail preference flips head/tail when configured. Object properties are ordered by key, and strings expand by grapheme with early characters prioritized over very deep expansions.
- - <sup><b>[3]</b></sup> <b>Choose top N nodes (binary search)</b>: Iteratively picks N so that the rendered preview fits within the character budget, looping between “choose N” and a render attempt to converge quickly.
+ - <sup><b>[3]</b></sup> <b>Choose top N nodes (binary search)</b>: Iteratively picks N so that the rendered preview fits within the byte budget, looping between “choose N” and a render attempt to converge quickly.
  - <sup><b>[4]</b></sup> <b>Render attempt</b>: Serializes the currently included nodes using the selected template. Omission summaries and per-file section headers appear in display templates (pseudo/js); json remains strict. For arrays, display templates may insert internal gap markers between non‑contiguous kept items using original indices.
  - <sup><b>[5]</b></sup> <b>Diagram source</b>: The Algorithm diagram is generated from `docs/diagrams/algorithm.mmd`. Regenerate the SVG with `cargo make diagrams` before releasing.
 

{headson-0.6.3 → headson-0.6.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "maturin"
 
 [project]
 name = "headson"
-version = "0.6.3"
+version = "0.6.5"
 description = "Budget‑constrained JSON preview renderer (Python bindings)"
 readme = "README.md"
 requires-python = ">=3.10"

{headson-0.6.3 → headson-0.6.5}/python/Cargo.lock

@@ -214,7 +214,7 @@ dependencies = [
 
 [[package]]
 name = "headson"
-version = "0.6.3"
+version = "0.6.5"
 dependencies = [
  "anyhow",
  "clap",
@@ -228,7 +228,7 @@ dependencies = [
 
 [[package]]
 name = "headson-python"
-version = "0.6.3"
+version = "0.6.5"
 dependencies = [
  "anyhow",
  "headson",

{headson-0.6.3 → headson-0.6.5}/python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "headson-python"
-version = "0.6.3"
+version = "0.6.5"
 edition = "2021"
 publish = false
 readme = "README.md"

{headson-0.6.3 → headson-0.6.5}/python/README.md

@@ -4,11 +4,11 @@ Minimal Python API for the `headson` preview renderer.
 
 API
 
-- `headson.summarize(text: str, *, format: str = "auto", style: str = "default", input_format: str = "json", character_budget: int | None = None, skew: str = "balanced") -> str`
+- `headson.summarize(text: str, *, format: str = "auto", style: str = "default", input_format: str = "json", byte_budget: int | None = None, skew: str = "balanced") -> str`
   - `format`: output format — `"auto" | "json" | "yaml" | "text"`.
   - `style`: output style — `"strict" | "default" | "detailed"`.
   - `input_format`: ingestion format — `"json" | "yaml" | "text"`.
-  - `character_budget`: maximum output size in characters (defaults to 500 if not set).
+  - `byte_budget`: maximum output size in bytes (defaults to 500 if not set).
   - `skew`: one of `"balanced" | "head" | "tail"`.
     - `balanced` (default), `head` keeps first N, `tail` keeps last N. Display styles place omission markers accordingly; strict JSON remains unannotated.
   - Notes:
@@ -20,26 +20,26 @@ Examples:
 import headson
 
 # Human-friendly JSON (Pseudo) with a small budget
-print(headson.summarize('{"a": 1, "b": [1,2,3]}', format="json", style="default", character_budget=80))
+print(headson.summarize('{"a": 1, "b": [1,2,3]}', format="json", style="default", byte_budget=80))
 
 # Strict JSON stays valid JSON
-print(headson.summarize('{"a": 1, "b": {"c": 2}}', format="json", style="strict", character_budget=10_000))
+print(headson.summarize('{"a": 1, "b": {"c": 2}}', format="json", style="strict", byte_budget=10_000))
 
 # Annotated JSON (JS) with tail skew: prefer the end of arrays when truncating
 arr = ','.join(str(i) for i in range(100))
-print(headson.summarize('{"arr": [' + arr + ']}', format="json", style="detailed", character_budget=60, skew="tail"))
+print(headson.summarize('{"arr": [' + arr + ']}', format="json", style="detailed", byte_budget=60, skew="tail"))
 
 # YAML styles: strict (no comments), default (… comments), detailed (counts)
 doc = 'root:\n  items: [1,2,3,4,5,6,7,8,9,10]\n'
-print(headson.summarize(doc, format="yaml", style="strict", input_format="yaml", character_budget=60))
-print(headson.summarize(doc, format="yaml", style="default", input_format="yaml", character_budget=60))
-print(headson.summarize(doc, format="yaml", style="detailed", input_format="yaml", character_budget=60))
+print(headson.summarize(doc, format="yaml", style="strict", input_format="yaml", byte_budget=60))
+print(headson.summarize(doc, format="yaml", style="default", input_format="yaml", byte_budget=60))
+print(headson.summarize(doc, format="yaml", style="detailed", input_format="yaml", byte_budget=60))
 
 # Note: tail mode affects only display styles; strict JSON stays strict.
 
 # Text: render raw lines with omission markers depending on style
 text = "one\ntwo\nthree\n"
-print(headson.summarize(text, format="text", style="default", input_format="text", character_budget=10))
+print(headson.summarize(text, format="text", style="default", input_format="text", byte_budget=10))
 ```
 
 Install for development:

{headson-0.6.3 → headson-0.6.5}/python/src/lib.rs

@@ -59,6 +59,7 @@ fn render_config_with_sampler(
         color_mode: ColorMode::Auto,
         color_enabled: false,
         style: s,
+        string_free_prefix_graphemes: None,
     })
 }
 
@@ -85,6 +86,7 @@ fn priority_config(
         prefer_tail_arrays,
         array_bias: headson_core::ArrayBias::HeadMidTail,
         array_sampler: sampler,
+        line_budget_only: false,
     }
 }
 
@@ -93,19 +95,19 @@ fn to_pyerr(e: anyhow::Error) -> PyErr {
 }
 
 #[pyfunction]
-#[pyo3(signature = (text, *, format="auto", style="default", character_budget=None, skew="balanced", input_format="json"))]
+#[pyo3(signature = (text, *, format="auto", style="default", byte_budget=None, skew="balanced", input_format="json"))]
 fn summarize(
     py: Python<'_>,
     text: &str,
     format: &str,
     style: &str,
-    character_budget: Option<usize>,
+    byte_budget: Option<usize>,
     skew: &str,
     input_format: &str,
 ) -> PyResult<String> {
     let sampler = parse_skew(skew).map_err(to_pyerr)?;
     let cfg = render_config_with_sampler(format, style, sampler).map_err(to_pyerr)?;
-    let budget = character_budget.unwrap_or(500);
+    let budget = byte_budget.unwrap_or(500);
     let per_file_for_priority = budget.max(1);
     let prio = priority_config(per_file_for_priority, sampler);
     let input = text.as_bytes().to_vec();

{headson-0.6.3/src/json_ingest → headson-0.6.5/src/ingest/formats/json}/builder.rs

@@ -5,7 +5,7 @@ use std::cell::RefCell;
 use crate::order::NodeKind;
 use crate::utils::tree_arena::{JsonTreeArena, JsonTreeNode};
 
-use super::samplers::ArraySamplerKind;
+use crate::ingest::sampling::ArraySamplerKind;
 
 #[derive(Default)]
 pub(crate) struct JsonTreeBuilder {
@@ -15,10 +15,7 @@ pub(crate) struct JsonTreeBuilder {
 }
 
 impl JsonTreeBuilder {
-    pub(crate) fn new(
-        array_cap: usize,
-        sampler: super::samplers::ArraySamplerKind,
-    ) -> Self {
+    pub(crate) fn new(array_cap: usize, sampler: ArraySamplerKind) -> Self {
         Self {
             arena: RefCell::new(JsonTreeArena::default()),
             array_cap,

{headson-0.6.3/src/json_ingest → headson-0.6.5/src/ingest/formats/json}/mod.rs

@@ -1,24 +1,27 @@
 mod builder;
 mod samplers;
-use serde::de::DeserializeSeed;
 
-use crate::PriorityConfig;
-use crate::utils::tree_arena::JsonTreeArena;
 use anyhow::Result;
 use builder::JsonTreeBuilder;
+use serde::de::DeserializeSeed;
+
+use crate::PriorityConfig;
+use crate::utils::tree_arena::JsonTreeArena as TreeArena;
+
+use crate::ingest::Ingest;
 
 #[cfg(test)]
 pub fn build_json_tree_arena(
     input: &str,
     config: &PriorityConfig,
-) -> Result<JsonTreeArena> {
+) -> Result<TreeArena> {
     build_json_tree_arena_from_bytes(input.as_bytes().to_vec(), config)
 }
 
 pub fn build_json_tree_arena_from_bytes(
     mut bytes: Vec<u8>,
     config: &PriorityConfig,
-) -> Result<JsonTreeArena> {
+) -> Result<TreeArena> {
     let mut de = simd_json::Deserializer::from_slice(&mut bytes)?;
     let builder = JsonTreeBuilder::new(
         config.array_max_items,
@@ -36,7 +39,7 @@ pub fn build_json_tree_arena_from_bytes(
 pub fn build_json_tree_arena_from_many(
     mut inputs: Vec<(String, Vec<u8>)>,
     config: &PriorityConfig,
-) -> Result<JsonTreeArena> {
+) -> Result<TreeArena> {
     let builder = JsonTreeBuilder::new(
         config.array_max_items,
         config.array_sampler.into(),
@@ -57,6 +60,38 @@ pub fn build_json_tree_arena_from_many(
     Ok(arena)
 }
 
+/// JSON adapter for the ingest boundary. Delegates to the JSON builder to
+/// produce the neutral `TreeArena`.
+pub struct JsonIngest;
+
+impl Ingest for JsonIngest {
+    fn parse_one(bytes: Vec<u8>, cfg: &PriorityConfig) -> Result<TreeArena> {
+        build_json_tree_arena_from_bytes(bytes, cfg)
+    }
+
+    fn parse_many(
+        inputs: Vec<(String, Vec<u8>)>,
+        cfg: &PriorityConfig,
+    ) -> Result<TreeArena> {
+        build_json_tree_arena_from_many(inputs, cfg)
+    }
+}
+
+/// Convenience functions for the JSON ingest path.
+pub fn parse_json_one(
+    bytes: Vec<u8>,
+    cfg: &PriorityConfig,
+) -> Result<TreeArena> {
+    JsonIngest::parse_one(bytes, cfg)
+}
+
+pub fn parse_json_many(
+    inputs: Vec<(String, Vec<u8>)>,
+    cfg: &PriorityConfig,
+) -> Result<TreeArena> {
+    JsonIngest::parse_many(inputs, cfg)
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;

{headson-0.6.3/src/json_ingest → headson-0.6.5/src/ingest/formats/json}/samplers/default.rs

@@ -1,14 +1,12 @@
 use serde::de::{IgnoredAny, SeqAccess};
 
-use super::{JsonTreeBuilder, SampledArray};
+use super::JsonTreeBuilder;
+use super::SampledArray;
 
-// Tunable sampling constants for the default strategy.
+// Default strategy phases: keep-first, greedy, then index-hash acceptance (~50%).
 const RANDOM_ACCEPT_SEED: u64 = 0x9e37_79b9_7f4a_7c15;
-// ~50% acceptance to thin remaining elements in the random phase.
-const RANDOM_ACCEPT_THRESHOLD: u32 = 0x8000_0000;
-// Keep a small, fixed number of items from the head before greedy/random phases.
+const RANDOM_ACCEPT_THRESHOLD: u32 = 0x8000_0000; // ~50%
 const KEEP_FIRST_COUNT: usize = 3;
-// Take roughly half of the remaining capacity greedily after the first items.
 const GREEDY_PORTION_DIVISOR: usize = 2;
 
 struct PhaseState {

{headson-0.6.3/src/json_ingest → headson-0.6.5/src/ingest/formats/json}/samplers/head.rs

@@ -1,6 +1,7 @@
 use serde::de::{IgnoredAny, SeqAccess};
 
-use super::{JsonTreeBuilder, SampledArray};
+use super::JsonTreeBuilder;
+use super::SampledArray;
 
 fn parse_keep<'de, A>(
     seq: &mut A,

{headson-0.6.3/src/json_ingest → headson-0.6.5/src/ingest/formats/json}/samplers/mod.rs

@@ -1,7 +1,7 @@
 use serde::de::SeqAccess;
 
-use crate::ArraySamplerStrategy;
-use crate::json_ingest::builder::JsonTreeBuilder;
+use crate::ingest::formats::json::builder::JsonTreeBuilder;
+use crate::ingest::sampling::ArraySamplerKind;
 
 #[derive(Debug)]
 pub(crate) struct SampledArray {
@@ -10,14 +10,6 @@ pub(crate) struct SampledArray {
     pub total_len: usize,
 }
 
-#[derive(Copy, Clone, Debug, Default)]
-pub(crate) enum ArraySamplerKind {
-    #[default]
-    Default,
-    Head,
-    Tail,
-}
-
 impl ArraySamplerKind {
     pub(crate) fn sample_stream<'de, A>(
         self,
@@ -38,16 +30,6 @@ impl ArraySamplerKind {
     }
 }
 
-impl From<ArraySamplerStrategy> for ArraySamplerKind {
-    fn from(strategy: ArraySamplerStrategy) -> Self {
-        match strategy {
-            ArraySamplerStrategy::Default => ArraySamplerKind::Default,
-            ArraySamplerStrategy::Head => ArraySamplerKind::Head,
-            ArraySamplerStrategy::Tail => ArraySamplerKind::Tail,
-        }
-    }
-}
-
 mod default;
 mod head;
 mod tail;

{headson-0.6.3/src/json_ingest → headson-0.6.5/src/ingest/formats/json}/samplers/tail.rs

@@ -1,6 +1,7 @@
 use serde::de::{IgnoredAny, SeqAccess};
 
-use super::{JsonTreeBuilder, SampledArray};
+use super::JsonTreeBuilder;
+use super::SampledArray;
 
 pub(crate) fn sample_stream<'de, A>(
     seq: &mut A,
@@ -89,8 +90,10 @@ mod tests {
         let mut cfg = PriorityConfig::new(usize::MAX, 5);
         cfg.array_sampler = crate::ArraySamplerStrategy::Tail;
         let arena =
-            crate::json_ingest::build_json_tree_arena_from_bytes(input, &cfg)
-                .expect("arena");
+            crate::ingest::formats::json::build_json_tree_arena_from_bytes(
+                input, &cfg,
+            )
+            .expect("arena");
         let root = &arena.nodes[arena.root_id];
         assert_eq!(root.children_len, 5, "kept 5");
         let mut orig_indices = Vec::new();