granit-parser - cargo Package Compare versions

Comparing version 0.0.4 to 0.0.5

.github/workflows/fuzz.yml

+name: Fuzz
+
+on:
+  pull_request:
+  push:
+    branches:
+      - master
+  schedule:
+    - cron: "30 3 * * 0"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: fuzz-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  fuzz:
+    name: Build and smoke-run fuzz targets
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    env:
+      CARGO_TERM_COLOR: always
+      FUZZ_SECONDS: ${{ github.event_name == 'schedule' && '1200' || '20' }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v5
+
+      - name: Install nightly Rust
+        run: rustup toolchain install nightly --profile minimal --no-self-update
+
+      - name: Rust cache
+        uses: Swatinem/rust-cache@v2
+
+      - name: Install cargo-fuzz
+        run: cargo +nightly install cargo-fuzz
+
+      - name: Build fuzz targets
+        run: cargo +nightly fuzz build
+
+      - name: Smoke-run fuzz targets
+        shell: bash
+        run: |
+          set -euo pipefail
+          for target in aliases_merges duplicate_keys flow_collections large_scalars; do
+            cargo +nightly fuzz run "${target}" -- -max_total_time="${FUZZ_SECONDS}" -timeout=10 -rss_limit_mb=4096
+          done

tests/flow_collections_fuzz_regression.rs

+use std::panic::{catch_unwind, AssertUnwindSafe};
+
+use granit_parser::Parser;
+
+const CRASH_CA24C2F5B1341124FCD324CBAAFCAA9A1F6D034C: &[u8] = &[
+    255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 10, 9, 35, 8, 10, 9, 255, 255, 255, 255,
+    255, 10, 9, 35, 8, 35, 91, 93, 58,
+];
+
+fn drain_str_parser(input: &str) {
+    for event in Parser::new_from_str(input) {
+        if event.is_err() {
+            break;
+        }
+    }
+}
+
+fn drain_iter_parser(input: &str) {
+    for event in Parser::new_from_iter(input.chars()) {
+        if event.is_err() {
+            break;
+        }
+    }
+}
+
+#[test]
+fn crash_ca24c2f5b1341124fcd324cbaafcaa9a1f6d034c_does_not_panic() {
+    let s = String::from_utf8_lossy(CRASH_CA24C2F5B1341124FCD324CBAAFCAA9A1F6D034C);
+    let inputs = [
+        format!("[{s}]"),
+        format!("{{{s}}}"),
+        format!("root: {{{s}}}\narray: [{s}]\n"),
+    ];
+
+    for input in inputs {
+        let result = catch_unwind(AssertUnwindSafe(|| drain_str_parser(&input)));
+        assert!(result.is_ok(), "str parser panicked for input: {input:?}");
+
+        let result = catch_unwind(AssertUnwindSafe(|| drain_iter_parser(&input)));
+        assert!(result.is_ok(), "iter parser panicked for input: {input:?}");
+    }
+}

.cargo_vcs_info.json

 {
   "git": {
-    "sha1": "ca296b7858b3fbd531794e7ecda5732f0bd8206f"
+    "sha1": "9359b0a65b0968c6c69a77138d4d007068f871f9"
   },
   "path_in_vcs": ""
 }

Cargo.lock

@@ -115,6 +115,5 @@ # This file is automatically @generated by Cargo.
 name = "granit-parser"
-version = "0.0.4"
+version = "0.0.5"
 dependencies = [
  "arraydeque",
- "clap",
  "libtest-mimic",
@@ -121,0 +120,0 @@ "smallvec",

Cargo.toml

@@ -16,3 +16,3 @@ # THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
 name = "granit-parser"
-version = "0.0.4"
+version = "0.0.5"
 authors = [
@@ -119,2 +119,6 @@ "Ethiraric <[e-mail]>",
 [[test]]
+name = "flow_collections_fuzz_regression"
+path = "tests/flow_collections_fuzz_regression.rs"
+
+[[test]]
 name = "fuzz"
@@ -191,5 +195,2 @@ path = "tests/fuzz.rs"
 
-[dev-dependencies.clap]
-version = "=4.5.48"
-
 [dev-dependencies.libtest-mimic]
@@ -196,0 +197,0 @@ version = "=0.8.1"

CHANGELOG.md

 # Changelog
-## v0.0.4
+## v0.0.5
 - Performance improvements on comment parsing
+- Added `Span::tag_start` metadata for parser-emitted tagged node events, so diagnostics can point
+  at the explicit tag token even when the node span starts on a later line.
+- Added `Tag::original_handle`, `Tag::original_parts`, and `Tag::original` so consumers can inspect
+  the tag handle as written before `%TAG` directive resolution and reconstruct normalized
+  author-facing tag spelling, including verbatim tags (breaking change).
 
+## v0.0.4
+  Retracted
 
@@ -6,0 +13,0 @@ ## v0.0.3

README.md

@@ -6,2 +6,3 @@ # granit-parser
 [![GitHub Workflow Status](https://img.shields.io/github/actions/workflow/status/bourumir-wyngs/granit-parser/ci.yml)](https://github.com/bourumir-wyngs/granit-parser/actions/workflows/ci.yml)
+[![Fuzz](https://github.com/bourumir-wyngs/granit-parser/actions/workflows/fuzz.yml/badge.svg)](https://github.com/bourumir-wyngs/granit-parser/actions/workflows/fuzz.yml)
 [![docs.rs](https://docs.rs/granit-parser/badge.svg)](https://docs.rs/granit-parser)
@@ -37,3 +38,3 @@ [![codecov](https://codecov.io/gh/bourumir-wyngs/granit-parser/graph/badge.svg)](https://codecov.io/gh/bourumir-wyngs/granit-parser)
 
-[`Parser::new_from_str`](https://docs.rs/granit-parser/latest/granit_parser/struct.Parser.html#method.new_from_str) returns an iterator of ([`Event`](https://docs.rs/granit-parser/latest/granit_parser/enum.Event.html), [`Span`](https://docs.rs/granit-parser/latest/granit_parser/struct.Span.html)) pairs. The event helpers expose common node metadata, and spans provide byte ranges plus source slices:
+[`Parser::new_from_str`](https://docs.rs/granit-parser/latest/granit_parser/struct.Parser.html#method.new_from_str) returns an iterator of ([`Event`](https://docs.rs/granit-parser/latest/granit_parser/enum.Event.html), [`Span`](https://docs.rs/granit-parser/latest/granit_parser/struct.Span.html)) pairs. The event helpers expose common node metadata, and spans provide byte ranges, source slices, and explicit tag-token starts for tagged nodes:
 
@@ -47,4 +48,7 @@ Comments are emitted as `Event::Comment(text, placement)`. They are presentation metadata for tools such as linters and formatters, not YAML data nodes, so consumers that build YAML values should filter them out. The companion `Span` for a comment covers the whole source comment, including `#` and excluding the line break; when parsing from `Parser::new_from_str`, `span.slice(yaml)` returns that source comment text.
     let yaml = r#"
+%TAG !example! tag:example.com,2000:
+---
 items: !shopping
   - milk
+  - !example!sliced bread
   - !!str bread
@@ -63,9 +67,16 @@ locations: # Example with composite keys
         if let Some(tag) = event.tag() {
+            let tag_start = span
+                .tag_start()
+                .map(|mark| (mark.line(), mark.col(), mark.byte_offset()));
+
             if let Some((value, _style)) = event.scalar() {
                 println!(
-                    "scalar tag: {tag} core-str={} for {value:?}",
+                    "scalar tag: {tag} core-str={} tag_start(line,col,byte)={tag_start:?} for {value:?}",
                     tag.is_yaml_core_schema_tag("str")
                 );
             } else if event.is_node() {
-                println!("node tag: {tag} custom={}", tag.is_custom());
+                println!(
+                    "node tag: {tag} custom={} tag_start(line,col,byte)={tag_start:?}",
+                    tag.is_custom()
+                );
             }
@@ -89,31 +100,33 @@ }
 StreamStart bytes=Some(0..0) source=Some("")
-DocumentStart(false) bytes=Some(1..1) source=Some("")
-MappingStart(Block, 0, None) bytes=Some(1..1) source=Some("")
-Scalar("items", Plain, 0, None) bytes=Some(1..6) source=Some("items")
-node tag: !shopping custom=true
-SequenceStart(Block, 0, Some(Tag { handle: "!", suffix: "shopping" })) bytes=Some(20..20) source=Some("")
-Scalar("milk", Plain, 0, None) bytes=Some(22..26) source=Some("milk")
-scalar tag: tag:yaml.org,2002:str core-str=true for "bread"
-Scalar("bread", Plain, 0, Some(Tag { handle: "tag:yaml.org,2002:", suffix: "str" })) bytes=Some(37..42) source=Some("bread")
-SequenceEnd bytes=Some(43..43) source=Some("")
-Scalar("locations", Plain, 0, None) bytes=Some(43..52) source=Some("locations")
-Comment(" Example with composite keys", Right) bytes=Some(54..83) source=Some("# Example with composite keys")
-MappingStart(Block, 0, None) bytes=Some(86..86) source=Some("")
-SequenceStart(Flow, 0, None) bytes=Some(86..87) source=Some("[")
-Scalar("47.3769", Plain, 0, None) bytes=Some(87..94) source=Some("47.3769")
-Scalar("8.5417", Plain, 0, None) bytes=Some(96..102) source=Some("8.5417")
-SequenceEnd bytes=Some(102..103) source=Some("]")
-Scalar("local", Plain, 0, None) bytes=Some(105..110) source=Some("local")
-SequenceStart(Flow, 0, None) bytes=Some(113..114) source=Some("[")
-Scalar("40.7128", Plain, 0, None) bytes=Some(114..121) source=Some("40.7128")
-Scalar("-74.0060", Plain, 0, None) bytes=Some(123..131) source=Some("-74.0060")
-SequenceEnd bytes=Some(131..132) source=Some("]")
-Scalar("remote", Plain, 0, None) bytes=Some(134..140) source=Some("remote")
-Comment(" JSON-style \\uXXXX surrogate pairs:", Above) bytes=Some(142..178) source=Some("# JSON-style \\uXXXX surrogate pairs:")
-MappingEnd bytes=Some(179..179) source=Some("")
-Scalar("music", Plain, 0, None) bytes=Some(179..184) source=Some("music")
-Scalar("𝄞🎵🎶", DoubleQuoted, 0, None) bytes=Some(186..224) source=Some("\"\\uD834\\uDD1E\\uD83C\\uDFB5\\uD83C\\uDFB6\"")
-MappingEnd bytes=Some(225..225) source=Some("")
-DocumentEnd bytes=Some(225..225) source=Some("")
-StreamEnd bytes=Some(225..225) source=Some("")
+DocumentStart(true) bytes=Some(38..41) source=Some("---")
+MappingStart(Block, 0, None) bytes=Some(42..42) source=Some("")
+Scalar("items", Plain, 0, None) bytes=Some(42..47) source=Some("items")
+node tag: !shopping custom=true tag_start(line,col,byte)=Some((4, 7, Some(49)))
+SequenceStart(Block, 0, Some(Tag { handle: "!", suffix: "shopping", original_handle: "!" })) bytes=Some(61..61) source=Some("")
+Scalar("milk", Plain, 0, None) bytes=Some(63..67) source=Some("milk")
+scalar tag: tag:example.com,2000:sliced core-str=false tag_start(line,col,byte)=Some((6, 4, Some(72))) for "bread"
+Scalar("bread", Plain, 0, Some(Tag { handle: "tag:example.com,2000:", suffix: "sliced", original_handle: "!example!" })) bytes=Some(88..93) source=Some("bread")
+scalar tag: tag:yaml.org,2002:str core-str=true tag_start(line,col,byte)=Some((7, 4, Some(98))) for "bread"
+Scalar("bread", Plain, 0, Some(Tag { handle: "tag:yaml.org,2002:", suffix: "str", original_handle: "!!" })) bytes=Some(104..109) source=Some("bread")
+SequenceEnd bytes=Some(110..110) source=Some("")
+Scalar("locations", Plain, 0, None) bytes=Some(110..119) source=Some("locations")
+Comment(" Example with composite keys", Right) bytes=Some(121..150) source=Some("# Example with composite keys")
+MappingStart(Block, 0, None) bytes=Some(153..153) source=Some("")
+SequenceStart(Flow, 0, None) bytes=Some(153..154) source=Some("[")
+Scalar("47.3769", Plain, 0, None) bytes=Some(154..161) source=Some("47.3769")
+Scalar("8.5417", Plain, 0, None) bytes=Some(163..169) source=Some("8.5417")
+SequenceEnd bytes=Some(169..170) source=Some("]")
+Scalar("local", Plain, 0, None) bytes=Some(172..177) source=Some("local")
+SequenceStart(Flow, 0, None) bytes=Some(180..181) source=Some("[")
+Scalar("40.7128", Plain, 0, None) bytes=Some(181..188) source=Some("40.7128")
+Scalar("-74.0060", Plain, 0, None) bytes=Some(190..198) source=Some("-74.0060")
+SequenceEnd bytes=Some(198..199) source=Some("]")
+Scalar("remote", Plain, 0, None) bytes=Some(201..207) source=Some("remote")
+Comment(" JSON-style \\uXXXX surrogate pairs:", Above) bytes=Some(209..245) source=Some("# JSON-style \\uXXXX surrogate pairs:")
+MappingEnd bytes=Some(246..246) source=Some("")
+Scalar("music", Plain, 0, None) bytes=Some(246..251) source=Some("music")
+Scalar("𝄞🎵🎶", DoubleQuoted, 0, None) bytes=Some(253..291) source=Some("\"\\uD834\\uDD1E\\uD83C\\uDFB5\\uD83C\\uDFB6\"")
+MappingEnd bytes=Some(292..292) source=Some("")
+DocumentEnd bytes=Some(292..292) source=Some("")
+StreamEnd bytes=Some(292..292) source=Some("")
 ```
@@ -233,7 +246,19 @@
 ### Improved ergonomics
-Release 0.0.3 includes ergonomic helpers such as `Event::tag`, `Event::scalar`,
-`Event::anchor_id`, `Event::alias_id`, `Event::is_node`, `Tag::parts`,
-`Tag::is_custom`, `Tag::is_yaml_core_schema_tag`, `Span::slice`, and
-`ParserStack::push_include`. See CHANGELOG.md for details.
+The following ergonomic helpers are available:
+- `Event::tag`
+- `Event::scalar`
+- `Event::anchor_id`
+- `Event::alias_id`
+- `Event::is_node`
+- `Tag::parts`
+- `Tag::original_parts`
+- `Tag::original`
+- `Tag::is_custom`
+- `Tag::is_yaml_core_schema_tag`
+- `Span::slice`
+- `Span::tag_start`
+- `ParserStack::push_include`
 
+See CHANGELOG.md for details.
+
 ## Tools
@@ -240,0 +265,0 @@

tests/readme.rs

@@ -33,9 +33,16 @@ use granit_parser::{Parser, ScanError};
         if let Some(tag) = event.tag() {
+            let tag_start = span
+                .tag_start()
+                .map(|mark| (mark.line(), mark.col(), mark.byte_offset()));
+
             if let Some((value, _style)) = event.scalar() {
                 lines.push(format!(
-                    "scalar tag: {tag} core-str={} for {value:?}",
+                    "scalar tag: {tag} core-str={} tag_start(line,col,byte)={tag_start:?} for {value:?}",
                     tag.is_yaml_core_schema_tag("str")
                 ));
             } else if event.is_node() {
-                lines.push(format!("node tag: {tag} custom={}", tag.is_custom()));
+                lines.push(format!(
+                    "node tag: {tag} custom={} tag_start(line,col,byte)={tag_start:?}",
+                    tag.is_custom()
+                ));
             }
@@ -42,0 +49,0 @@ }

tests/span.rs

@@ -75,2 +75,3 @@ #![allow(clippy::bool_assert_comparison)]
     assert_eq!(span.byte_range(), Some(5..13));
+    assert_eq!(span.tag_start(), None);
 
@@ -86,2 +87,69 @@ let empty = granit_parser::Span::empty(Marker::new(6, 1, 6).with_byte_offset(Some(13)));
 #[test]
+fn tagged_block_collection_reports_tag_start_on_tag_line() {
+    let yaml = "key: !!omap # tag is here\n  a: 1\n";
+    let (_event, span) = Parser::new_from_str(yaml)
+        .map(Result::unwrap)
+        .find(|(event, _span)| {
+            matches!(
+                event,
+                Event::MappingStart(_, _, Some(tag)) if tag.suffix == "omap"
+            )
+        })
+        .expect("expected tagged block mapping");
+
+    assert_eq!(span.start.line(), 2);
+
+    let tag_start = span
+        .tag_start()
+        .expect("tagged node should report tag start");
+    assert_eq!(tag_start.line(), 1);
+    assert_eq!(tag_start.col(), 5);
+    assert_eq!(tag_start.byte_offset(), Some(5));
+}
+
+#[test]
+fn tag_start_uses_tag_token_when_anchor_precedes_tag() {
+    let yaml = "key: &a !!str value\n";
+    let (_event, span) = Parser::new_from_str(yaml)
+        .map(Result::unwrap)
+        .find(|(event, _span)| {
+            matches!(
+                event,
+                Event::Scalar(value, _, _, Some(tag))
+                    if value.as_ref() == "value" && tag.suffix == "str"
+            )
+        })
+        .expect("expected tagged anchored scalar");
+
+    let tag_start = span
+        .tag_start()
+        .expect("tagged node should report tag start");
+    assert_eq!(tag_start.line(), 1);
+    assert_eq!(tag_start.col(), 8);
+    assert_eq!(tag_start.byte_offset(), Some(8));
+}
+
+#[test]
+fn tag_start_uses_tag_token_when_tag_precedes_anchor() {
+    let yaml = "key: !!str &a value\n";
+    let (_event, span) = Parser::new_from_str(yaml)
+        .map(Result::unwrap)
+        .find(|(event, _span)| {
+            matches!(
+                event,
+                Event::Scalar(value, _, _, Some(tag))
+                    if value.as_ref() == "value" && tag.suffix == "str"
+            )
+        })
+        .expect("expected tagged anchored scalar");
+
+    let tag_start = span
+        .tag_start()
+        .expect("tagged node should report tag start");
+    assert_eq!(tag_start.line(), 1);
+    assert_eq!(tag_start.col(), 5);
+    assert_eq!(tag_start.byte_offset(), Some(5));
+}
+
+#[test]
 fn span_slice_returns_source_text_for_valid_byte_ranges() {
@@ -88,0 +156,0 @@ let source = "key: value";

No alert changes

No metric changes