headson 0.6.2__tar.gz → 0.6.4__tar.gz

{headson-0.6.2 → headson-0.6.4}/Cargo.lock

@@ -298,7 +298,7 @@ dependencies = [
 
 [[package]]
 name = "headson"
-version = "0.6.2"
+version = "0.6.4"
 dependencies = [
  "anyhow",
  "assert_cmd",

{headson-0.6.2 → headson-0.6.4}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "headson"
-version = "0.6.2"
+version = "0.6.4"
 edition = "2024"
 description = "Budget‑constrained JSON preview renderer"
 readme = "README.md"

{headson-0.6.2 → headson-0.6.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: headson
-Version: 0.6.2
+Version: 0.6.4
 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>
 
-Head/tail for JSON and 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.
+`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.)
 
 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:
@@ -41,10 +44,11 @@ From source:
 ## Features
 
 - Budgeted output: specify exactly how much you want to see
-- Output formats: `auto | json | yaml`
+- Output formats: `auto | json | yaml | text`
   - Styles: `strict | default | detailed`
     - JSON family: `strict` → strict JSON, `default` → human‑friendly Pseudo, `detailed` → JS with inline comments
     - YAML: always YAML; `strict` has no comments, `default` uses “# …”, `detailed` uses “# N more …”
+    - Text: prints raw lines. In `default` style, omissions are shown as a single line `…`; in `detailed`, as `… N more lines …`. `strict` omits array‑level summaries.
 - Multiple inputs: preview many files at once with a shared or per‑file budget
 - Fast: processes gigabyte‑scale files in seconds (mostly disk‑bound)
 - Available as a CLI app and as a Python library
@@ -66,14 +70,14 @@ 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.
-- `-f, --format <auto|json|yaml>`: output format (default: `auto`).
-  - Auto: stdin → JSON family; filesets → per‑file based on extension (`.json` → JSON family, `.yaml`/`.yml` → YAML).
+- `-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`).
   - JSON family: `strict` → strict JSON; `default` → Pseudo; `detailed` → JS with inline comments.
   - YAML: always YAML; style only affects comments (`strict` none, `default` “# …”, `detailed` “# N more …”).
-- `-i, --input-format <json|yaml>`: ingestion format (default: `json`). For filesets in `auto` format, ingestion is chosen by extensions.
+- `-i, --input-format <json|yaml|text>`: ingestion format (default: `json`). For filesets in `auto` format, ingestion is chosen by extensions.
 - `-m, --compact`: no indentation, no spaces, no newlines
 - `--no-newline`: single line output
 - `--no-space`: no space after `:` in objects
@@ -86,8 +90,9 @@ Notes:
 
 - Multiple inputs:
   - 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`.
-  - `--global-budget` may truncate or omit entire files to respect the total budget.
+- 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-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.
@@ -96,24 +101,45 @@ 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 -c 200 notes.txt
+
+- Force Text ingest/output (useful when mixing with other extensions):
+
+      headson -c 200 -i text -f text notes.txt
+
+- Many text files (fileset):
+
+      headson -c 800 -i text -f text logs/*.txt
+
+- Styles on Text:
+  - default: omission as a standalone `…` line.
+  - detailed: omission as `… N more lines …`.
+  - strict: no array‑level omission line (individual long lines may still truncate with `…`).
 
 Show help:
 
     headson --help
 
+Note: flags align with head/tail conventions (`-c/--bytes`, `-C/--global-bytes`).
+
 ## Examples: head vs headson
 
 Input:
@@ -132,7 +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", … ] },
@@ -145,7 +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}}
 ```
 
@@ -157,6 +183,7 @@ Regenerate locally:
 - Run: cargo make tapes
 - Outputs are written to docs/assets/tapes
 
+
 ## Python Bindings
 
 A thin Python extension module is available on PyPI as `headson`.

{headson-0.6.2 → headson-0.6.4}/README.md

@@ -6,12 +6,15 @@
   <br/>
 </p>
 
-Head/tail for JSON and 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.
+`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.)
 
 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:
@@ -27,10 +30,11 @@ From source:
 ## Features
 
 - Budgeted output: specify exactly how much you want to see
-- Output formats: `auto | json | yaml`
+- Output formats: `auto | json | yaml | text`
   - Styles: `strict | default | detailed`
     - JSON family: `strict` → strict JSON, `default` → human‑friendly Pseudo, `detailed` → JS with inline comments
     - YAML: always YAML; `strict` has no comments, `default` uses “# …”, `detailed` uses “# N more …”
+    - Text: prints raw lines. In `default` style, omissions are shown as a single line `…`; in `detailed`, as `… N more lines …`. `strict` omits array‑level summaries.
 - Multiple inputs: preview many files at once with a shared or per‑file budget
 - Fast: processes gigabyte‑scale files in seconds (mostly disk‑bound)
 - Available as a CLI app and as a Python library
@@ -52,14 +56,14 @@ 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.
-- `-f, --format <auto|json|yaml>`: output format (default: `auto`).
-  - Auto: stdin → JSON family; filesets → per‑file based on extension (`.json` → JSON family, `.yaml`/`.yml` → YAML).
+- `-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`).
   - JSON family: `strict` → strict JSON; `default` → Pseudo; `detailed` → JS with inline comments.
   - YAML: always YAML; style only affects comments (`strict` none, `default` “# …”, `detailed` “# N more …”).
-- `-i, --input-format <json|yaml>`: ingestion format (default: `json`). For filesets in `auto` format, ingestion is chosen by extensions.
+- `-i, --input-format <json|yaml|text>`: ingestion format (default: `json`). For filesets in `auto` format, ingestion is chosen by extensions.
 - `-m, --compact`: no indentation, no spaces, no newlines
 - `--no-newline`: single line output
 - `--no-space`: no space after `:` in objects
@@ -72,8 +76,9 @@ Notes:
 
 - Multiple inputs:
   - 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`.
-  - `--global-budget` may truncate or omit entire files to respect the total budget.
+- 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-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.
@@ -82,24 +87,45 @@ 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 -c 200 notes.txt
+
+- Force Text ingest/output (useful when mixing with other extensions):
+
+      headson -c 200 -i text -f text notes.txt
+
+- Many text files (fileset):
+
+      headson -c 800 -i text -f text logs/*.txt
+
+- Styles on Text:
+  - default: omission as a standalone `…` line.
+  - detailed: omission as `… N more lines …`.
+  - strict: no array‑level omission line (individual long lines may still truncate with `…`).
 
 Show help:
 
     headson --help
 
+Note: flags align with head/tail conventions (`-c/--bytes`, `-C/--global-bytes`).
+
 ## Examples: head vs headson
 
 Input:
@@ -118,7 +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", … ] },
@@ -131,7 +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}}
 ```
 
@@ -143,6 +169,7 @@ Regenerate locally:
 - Run: cargo make tapes
 - Outputs are written to docs/assets/tapes
 
+
 ## Python Bindings
 
 A thin Python extension module is available on PyPI as `headson`.

{headson-0.6.2 → headson-0.6.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "maturin"
 
 [project]
 name = "headson"
-version = "0.6.2"
+version = "0.6.4"
 description = "Budget‑constrained JSON preview renderer (Python bindings)"
 readme = "README.md"
 requires-python = ">=3.10"

{headson-0.6.2 → headson-0.6.4}/python/Cargo.lock

@@ -214,7 +214,7 @@ dependencies = [
 
 [[package]]
 name = "headson"
-version = "0.6.2"
+version = "0.6.4"
 dependencies = [
  "anyhow",
  "clap",
@@ -228,7 +228,7 @@ dependencies = [
 
 [[package]]
 name = "headson-python"
-version = "0.6.2"
+version = "0.6.4"
 dependencies = [
  "anyhow",
  "headson",

{headson-0.6.2 → headson-0.6.4}/python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "headson-python"
-version = "0.6.2"
+version = "0.6.4"
 edition = "2021"
 publish = false
 readme = "README.md"

{headson-0.6.2 → headson-0.6.4}/python/README.md

@@ -5,9 +5,9 @@ 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`
-  - `format`: output format — `"auto" | "json" | "yaml"`.
+  - `format`: output format — `"auto" | "json" | "yaml" | "text"`.
   - `style`: output style — `"strict" | "default" | "detailed"`.
-  - `input_format`: ingestion format — `"json" | "yaml"`.
+  - `input_format`: ingestion format — `"json" | "yaml" | "text"`.
   - `character_budget`: maximum output size in characters (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.
@@ -36,6 +36,10 @@ print(headson.summarize(doc, format="yaml", style="default", input_format="yaml"
 print(headson.summarize(doc, format="yaml", style="detailed", input_format="yaml", character_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))
 ```
 
 Install for development:

{headson-0.6.2 → headson-0.6.4}/python/src/lib.rs

@@ -31,7 +31,11 @@ fn map_output_template(format: &str, style: Style) -> Result<OutputTemplate> {
         "auto" => Ok(map_json_template_for_style(style)), // stdin => JSON family
         "json" => Ok(map_json_template_for_style(style)),
         "yaml" | "yml" => Ok(OutputTemplate::Yaml),
-        other => bail!("unknown format: {} (expected 'auto' | 'json' | 'yaml')", other),
+        "text" => Ok(OutputTemplate::Text),
+        other => bail!(
+            "unknown format: {} (expected 'auto' | 'json' | 'yaml' | 'text')",
+            other
+        ),
     }
 }
 
@@ -107,14 +111,12 @@ fn summarize(
     let input = text.as_bytes().to_vec();
     py.detach(|| {
         match input_format.to_ascii_lowercase().as_str() {
-            "json" => headson_core::headson(input, &cfg, &prio, budget)
+            "json" => headson_core::headson(input, &cfg, &prio, budget).map_err(to_pyerr),
+            "yaml" | "yml" => headson_core::headson_yaml(input, &cfg, &prio, budget)
                 .map_err(to_pyerr),
-            "yaml" | "yml" => {
-                headson_core::headson_yaml(input, &cfg, &prio, budget)
-                    .map_err(to_pyerr)
-            }
+            "text" => headson_core::headson_text(input, &cfg, &prio, budget).map_err(to_pyerr),
             other => Err(to_pyerr(anyhow::anyhow!(
-                "unknown input_format: {} (expected 'json' | 'yaml')",
+                "unknown input_format: {} (expected 'json' | 'yaml' | 'text')",
                 other
             ))),
         }

{headson-0.6.2/src/json_ingest → headson-0.6.4/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-0.6.2/src/json_ingest → headson-0.6.4/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-0.6.2/src/json_ingest → headson-0.6.4/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-0.6.2/src/json_ingest → headson-0.6.4/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-0.6.2/src/json_ingest → headson-0.6.4/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-0.6.2/src/json_ingest → headson-0.6.4/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();

headson-0.6.4/src/ingest/formats/mod.rs

@@ -0,0 +1,9 @@
+// File-format specific ingest adapters live under this module.
+pub mod json;
+pub mod text;
+pub mod yaml;
+
+// Re-export commonly used helpers for convenience
+pub use json::{parse_json_many, parse_json_one};
+pub use text::{parse_text_many, parse_text_one};
+pub use yaml::{parse_yaml_many, parse_yaml_one};