rumdl 0.0.153__tar.gz → 0.0.155__tar.gz

{rumdl-0.0.153 → rumdl-0.0.155}/Cargo.lock

@@ -901,12 +901,6 @@ dependencies = [
  "hashbrown 0.16.0",
 ]
 
-[[package]]
-name = "indoc"
-version = "2.0.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f4c7245a08504955605670dbf141fceab975f15ca21570696aebe9d2e71576bd"
-
 [[package]]
 name = "inotify"
 version = "0.9.6"
@@ -1131,15 +1125,6 @@ dependencies = [
  "libc",
 ]
 
-[[package]]
-name = "memoffset"
-version = "0.9.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "488016bfae457b036d996092f6cb448677611ce4449e970ceaf42695203f218a"
-dependencies = [
- "autocfg",
-]
-
 [[package]]
 name = "mimalloc"
 version = "0.1.48"
@@ -1462,69 +1447,6 @@ version = "0.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "007d8adb5ddab6f8e3f491ac63566a7d5002cc7ed73901f72057943fa71ae1ae"
 
-[[package]]
-name = "pyo3"
-version = "0.24.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e5203598f366b11a02b13aa20cab591229ff0a89fd121a308a5df751d5fc9219"
-dependencies = [
- "cfg-if",
- "indoc",
- "libc",
- "memoffset",
- "once_cell",
- "portable-atomic",
- "pyo3-build-config",
- "pyo3-ffi",
- "pyo3-macros",
- "unindent",
-]
-
-[[package]]
-name = "pyo3-build-config"
-version = "0.24.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "99636d423fa2ca130fa5acde3059308006d46f98caac629418e53f7ebb1e9999"
-dependencies = [
- "once_cell",
- "target-lexicon",
-]
-
-[[package]]
-name = "pyo3-ffi"
-version = "0.24.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "78f9cf92ba9c409279bc3305b5409d90db2d2c22392d443a87df3a1adad59e33"
-dependencies = [
- "libc",
- "pyo3-build-config",
-]
-
-[[package]]
-name = "pyo3-macros"
-version = "0.24.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b999cb1a6ce21f9a6b147dcf1be9ffedf02e0043aec74dc390f3007047cecd9"
-dependencies = [
- "proc-macro2",
- "pyo3-macros-backend",
- "quote",
- "syn",
-]
-
-[[package]]
-name = "pyo3-macros-backend"
-version = "0.24.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "822ece1c7e1012745607d5cf0bcb2874769f0f7cb34c4cde03b9358eb9ef911a"
-dependencies = [
- "heck",
- "proc-macro2",
- "pyo3-build-config",
- "quote",
- "syn",
-]
-
 [[package]]
 name = "quick-error"
 version = "1.2.3"
@@ -1644,7 +1566,7 @@ checksum = "caf4aa5b0f434c91fe5c7f1ecb6a5ece2130b02ad2a590589dda5146df959001"
 
 [[package]]
 name = "rumdl"
-version = "0.0.153"
+version = "0.0.155"
 dependencies = [
  "anyhow",
  "assert_cmd",
@@ -1671,12 +1593,10 @@ dependencies = [
  "pretty_assertions",
  "proptest",
  "pulldown-cmark",
- "pyo3",
  "rand",
  "rayon",
  "regex",
  "schemars",
- "seahash",
  "serde",
  "serde_json",
  "serde_yaml",
@@ -1691,8 +1611,6 @@ dependencies = [
  "tower 0.5.2",
  "tower-lsp",
  "tower-service",
- "unicode-bidi",
- "unicode-blocks",
  "unicode-normalization",
  "unicode-segmentation",
  "unicode-width",
@@ -1781,12 +1699,6 @@ version = "1.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
 
-[[package]]
-name = "seahash"
-version = "4.1.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1c107b6f4780854c8b126e228ea8869f4d7b71260f962fefb57b996b8959ba6b"
-
 [[package]]
 name = "serde"
 version = "1.0.226"
@@ -1945,12 +1857,6 @@ dependencies = [
  "syn",
 ]
 
-[[package]]
-name = "target-lexicon"
-version = "0.13.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "df7f62577c25e07834649fc3b39fafdc597c0a3527dc1c60129201ccfcbaa50c"
-
 [[package]]
 name = "tempfile"
 version = "3.22.0"
@@ -2243,18 +2149,6 @@ version = "2.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "75b844d17643ee918803943289730bec8aac480150456169e647ed0b576ba539"
 
-[[package]]
-name = "unicode-bidi"
-version = "0.3.18"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5c1cb5db39152898a79168971543b1cb5020dff7fe43c8dc468b0885f5e29df5"
-
-[[package]]
-name = "unicode-blocks"
-version = "0.1.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6b12e05d9e06373163a9bb6bb8c263c261b396643a99445fe6b9811fd376581b"
-
 [[package]]
 name = "unicode-id"
 version = "0.3.6"
@@ -2288,12 +2182,6 @@ version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4a1a07cc7db3810833284e8d372ccdc6da29741639ecc70c9ec107df0fa6154c"
 
-[[package]]
-name = "unindent"
-version = "0.2.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7264e107f553ccae879d21fbea1d6724ac785e8c3bfc762137959b5802826ef3"
-
 [[package]]
 name = "unsafe-libyaml"
 version = "0.2.11"

{rumdl-0.0.153 → rumdl-0.0.155}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "rumdl"
-version = "0.0.153"
+version = "0.0.155"
 edition = "2024"
 rust-version = "1.89.0"
 description = "A fast Markdown linter written in Rust (Ru(st) MarkDown Linter)"
@@ -18,7 +18,7 @@ default-run = "rumdl"  # Default binary for cargo run
 
 [lib]
 name = "rumdl_lib"
-crate-type = ["cdylib", "rlib"]
+crate-type = ["rlib"]
 
 [[bin]]
 name = "rumdl"
@@ -91,7 +91,6 @@ serde_yaml = "0.9.34"
 serde_json = "1.0"
 toml = "0.8.20"
 strsim = "0.11"
-pyo3 = { version = "0.24.1", features = ["extension-module", "abi3-py37"], optional = true }
 thiserror = "2.0.12"
 once_cell = "1.21.3"
 globset = "0.4.16"
@@ -105,7 +104,6 @@ dyn-clone = "1"
 url = { version = "2", features = ["serde"] }
 unicode-normalization = "0.1"
 memmap2 = "0.9"
-seahash = "4.1"
 schemars = "0.8"
 
 # LSP dependencies
@@ -124,8 +122,6 @@ etcetera = "0.8"
 default = ["parallel"]
 parallel = ["rayon"]
 profiling = []
-python = ["pyo3"]
-structure_preprocessing = []
 build-benchmarks = []
 
 [dev-dependencies]
@@ -138,8 +134,6 @@ rand = "0.9.1"
 pretty_assertions = "1.4"
 unicode-segmentation = "1.12"
 unicode-width = "0.2"
-unicode-blocks = "0.1"
-unicode-bidi = "0.3"
 
 [target.'cfg(not(target_env = "msvc"))'.dependencies]
 tikv-jemallocator = "0.6"

{rumdl-0.0.153 → rumdl-0.0.155}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rumdl
-Version: 0.0.153
+Version: 0.0.155
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers

rumdl-0.0.155/docs/LINTCONTEXT_OPTIMIZATION_PLAN.md

@@ -0,0 +1,311 @@
+# LintContext Optimization Implementation Plan
+
+## Overview
+
+This document outlines the plan to optimize 54 rules that aren't using LintContext's early-exit optimization methods. The optimizations replace O(n) string scanning with O(1) cached character
+frequency lookups.
+
+## Analysis Summary
+
+- **Total rules analyzed**: 54 rules without LintContext optimizations
+- **Agent analysis completed**: 10 representative rules across different categories
+- **Expected impact**: 10-100x speedup for documents without relevant markdown elements
+
+## Optimization Categories
+
+### Category 1: Direct Replacements (High Impact, Low Risk)
+
+These rules can directly replace string scanning with LintContext methods.
+
+#### 1. MD003 - Heading Style
+
+**File**: `src/rules/md003_heading_style.rs`
+**Current**: `!ctx.lines.iter().any(|line| line.heading.is_some())`
+**Optimized**: `!ctx.likely_has_headings()`
+**Location**: Line 237-240 in `should_skip()`
+**Impact**: O(n) line iteration → O(1) character frequency check
+
+#### 2. MD004 - Unordered List Style
+
+**File**: `src/rules/md004_unordered_list_style.rs`
+**Current**: `!ctx.content.contains(['*', '-', '+'])`
+**Optimized**: `!ctx.likely_has_lists()`
+**Locations**:
+
+- Line 107-109 in `check()`
+- Line 317 in `should_skip()`
+**Impact**: O(n) string scan → O(1) integer comparison
+
+#### 3. MD033 - No Inline HTML
+
+**File**: `src/rules/md033_no_inline_html.rs`
+**Current**: `!has_html_tags(content)` (custom function)
+**Optimized**: `!ctx.likely_has_html()`
+**Locations**:
+
+- Line 287 in `check()`
+- Line 438 in `should_skip()`
+**Impact**: Eliminates redundant '<' character scanning
+
+#### 4. MD042 - No Empty Links
+
+**File**: `src/rules/md042_no_empty_links.rs`
+**Current**: `!content.contains('[')`
+**Optimized**: `!ctx.likely_has_links_or_images()`
+**Location**: `should_skip()` method
+**Impact**: O(n) string scan → O(1) bracket count check
+
+#### 5. MD049 - Emphasis Style
+
+**File**: `src/rules/md049_emphasis_style.rs`
+**Current**: `!ctx.content.contains('*') && !ctx.content.contains('_')`
+**Optimized**: `!ctx.likely_has_emphasis()`
+**Locations**:
+
+- Line 113-115 in `check()`
+- Line 247 in `should_skip()`
+
+**Impact**: Two O(n) scans → O(1) check (asterisk_count > 1 || underscore_count > 1)
+
+#### 6. MD050 - Strong Style
+
+**File**: `src/rules/md050_strong_style.rs`
+**Current**: Similar to MD049 (checks for ** and __)
+**Optimized**: Create `ctx.likely_has_strong()` or use `likely_has_emphasis()`
+**Impact**: Same as MD049
+
+#### 7. MD055 - Table Pipe Style
+
+**File**: `src/rules/md055_table_pipe_style.rs`
+**Current**: `!ctx.content.contains('|')`
+**Optimized**: `!ctx.likely_has_tables()`
+**Locations**:
+
+- Line 174-177 in `should_skip()`
+- Line 185-187 in `check()` (remove - redundant)
+**Impact**: O(n) scan → O(1) check (pipe_count > 2)
+
+#### 8. MD027 - Multiple Spaces in Blockquote
+
+**File**: `src/rules/md027_multiple_spaces_blockquote.rs`
+**Current**: `!ctx.content.contains('>')`
+**Optimized**: `!ctx.likely_has_blockquotes()`
+**Location**: Line 192 in `should_skip()`
+**Impact**: O(n) scan → O(1) check (gt_count > 0)
+
+### Category 2: Compound Checks (Medium Impact)
+
+#### 9. MD040 - Fenced Code Language
+
+**File**: `src/rules/md040_fenced_code_language.rs`
+**Current**: `!content.contains("```") && !content.contains("~~~")`
+**Optimized**: `!ctx.likely_has_code() && !ctx.has_char('~')`
+**Location**: Line 341-344 in `should_skip()`
+**Impact**: Two O(n) substring scans → O(1) + O(n) character check
+**Note**: `likely_has_code()` only checks backticks; need separate tilde check
+
+#### 10. MD031 - Blanks Around Fences
+
+**File**: `src/rules/md031_blanks_around_fences.rs`
+**Current**: TBD (needs analysis)
+**Optimized**: Use `ctx.likely_has_code()`
+**Impact**: TBD
+
+#### 11. MD046 - Code Block Style
+
+**File**: `src/rules/md046_code_block_style.rs`
+**Current**: TBD (needs analysis)
+**Optimized**: Use `ctx.likely_has_code()`
+**Impact**: TBD
+
+#### 12. MD048 - Code Fence Style
+
+**File**: `src/rules/md048_code_fence_style.rs`
+**Current**: TBD (needs analysis)
+**Optimized**: Use `ctx.likely_has_code()`
+**Impact**: TBD
+
+### Category 3: Heading-Related Rules
+
+Apply `ctx.likely_has_headings()` to these rules:
+
+- MD001 - Heading Increment
+- MD002 - First Heading H1
+- MD018 - No Missing Space ATX
+- MD019 - No Multiple Space ATX
+- MD020 - No Missing Space Closed ATX
+- MD021 - No Multiple Space Closed ATX
+- MD022 - Blanks Around Headings
+- MD023 - Heading Start Left
+- MD024 - No Duplicate Heading
+- MD025 - Single Title
+- MD026 - No Trailing Punctuation
+- MD041 - First Line Heading
+- MD043 - Required Headings
+
+### Category 4: List-Related Rules
+
+Apply `ctx.likely_has_lists()` to these rules:
+
+- MD005 - List Indent
+- MD006 - Start Bullets
+- MD007 - UL Indent
+- MD029 - Ordered List Prefix
+- MD030 - List Marker Space
+- MD032 - Blanks Around Lists
+
+### Category 5: Link/Image-Related Rules
+
+Apply `ctx.likely_has_links_or_images()` to these rules:
+
+- MD011 - No Reversed Links
+- MD034 - No Bare URLs
+- MD039 - No Space in Links
+- MD045 - No Alt Text
+- MD051 - Link Fragments
+- MD052 - Reference Links/Images
+- MD053 - Link Image Reference Definitions
+- MD054 - Link Image Style
+- MD057 - Existing Relative Links
+
+### Category 6: Emphasis/Strong-Related Rules
+
+Apply `ctx.likely_has_emphasis()` to these rules:
+
+- MD036 - No Emphasis Only First
+- MD037 - Spaces Around Emphasis
+- MD038 - No Space in Code
+
+### Category 7: Blockquote-Related Rules
+
+Apply `ctx.likely_has_blockquotes()` to these rules:
+
+- MD028 - No Blanks in Blockquote
+
+### Category 8: Table-Related Rules
+
+Apply `ctx.likely_has_tables()` to these rules:
+
+- MD056 - Table Column Count
+- MD058 - Blanks Around Tables
+
+### Category 9: Simple Character Checks
+
+These rules need custom optimization using `has_char()`:
+
+- MD009 - Trailing Spaces (already optimized, uses `has_char(' ')`)
+- MD010 - No Hard Tabs (use `has_char('\t')`, consider adding tab_count to CharFrequency)
+- MD012 - No Multiple Blanks (check for '\n')
+- MD035 - HR Style (check for '-', '*', '_')
+- MD047 - Single Trailing Newline (check for '\n')
+
+### Category 10: Special Cases
+
+- MD014 - Commands Show Output (check for '```' or code blocks)
+- MD044 - Proper Names (no early exit possible - must scan all text)
+
+## Architectural Improvements
+
+### Add tab_count to CharFrequency
+
+**File**: `src/lint_context.rs`
+
+Add to CharFrequency struct (around line 289):
+
+```rust
+/// Count of \t characters (tabs)
+pub tab_count: usize,
+```
+
+Update `compute_char_frequency()` (around line 2240):
+
+```rust
+'\t' => frequency.tab_count += 1,
+```
+
+Update `has_char()` (around line 644):
+
+```rust
+'\t' => self.char_frequency.tab_count > 0,
+```
+
+Update `char_count()` (around line 663):
+
+```rust
+'\t' => self.char_frequency.tab_count,
+```
+
+## Implementation Strategy
+
+### Phase 1: Quick Wins (Category 1 - 8 rules)
+
+Implement direct replacements with minimal risk:
+
+- MD003, MD004, MD033, MD042, MD049, MD055, MD027, MD040
+
+### Phase 2: Systematic Rollout (Categories 3-8 - ~40 rules)
+
+Apply pattern-based optimizations to rule categories:
+
+- Heading rules → `likely_has_headings()`
+- List rules → `likely_has_lists()`
+- Link/image rules → `likely_has_links_or_images()`
+- Emphasis rules → `likely_has_emphasis()`
+- Blockquote rules → `likely_has_blockquotes()`
+- Table rules → `likely_has_tables()`
+
+### Phase 3: Architecture (Category 9)
+
+- Add `tab_count` to CharFrequency
+- Add `space_count` to CharFrequency (optional)
+- Add `newline_count` to CharFrequency (optional)
+
+### Phase 4: Validation
+
+- Run full test suite after each phase
+- Benchmark performance improvements
+- Verify no false negatives introduced
+
+## Expected Performance Impact
+
+### Documents Without Relevant Elements
+
+- **Before**: O(n) string/line scanning on every rule
+- **After**: O(1) character frequency check
+- **Speedup**: 10-100x depending on document size
+
+### Documents With Relevant Elements
+
+- **Before**: O(n) scan + rule processing
+- **After**: O(1) check + rule processing
+- **Speedup**: Minimal (rule still needs to run)
+
+### Overall Impact
+
+- **Typical workload**: 10-30% faster (mix of documents with/without elements)
+- **Best case**: 100x faster (processing large files without relevant markdown)
+- **Worst case**: No regression (documents with elements still process normally)
+
+## Testing Strategy
+
+For each optimized rule:
+
+1. Ensure existing tests pass
+2. Add test for empty document (should skip)
+3. Add test for document without relevant elements (should skip)
+4. Verify no false negatives (all violations still caught)
+
+## Rollout Plan
+
+1. **Week 1**: Implement Phase 1 (8 quick wins)
+2. **Week 2**: Implement Phase 2 (40 systematic rollouts)
+3. **Week 3**: Implement Phase 3 (architecture improvements)
+4. **Week 4**: Validation and benchmarking
+
+## Success Metrics
+
+- All 54 rules use appropriate LintContext optimization methods
+- Test suite passes with 100% success
+- No false negatives introduced
+- Measurable performance improvement (>10% on typical workloads)
+- Code consistency across all rules