html-to-markdown 2.30.0 → 3.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/Gemfile.lock +6 -19
- data/README.md +37 -50
- data/ext/html-to-markdown-rb/native/Cargo.lock +13 -701
- data/ext/html-to-markdown-rb/native/Cargo.toml +1 -4
- data/ext/html-to-markdown-rb/native/README.md +4 -13
- data/ext/html-to-markdown-rb/native/src/conversion/inline_images.rs +2 -73
- data/ext/html-to-markdown-rb/native/src/conversion/metadata.rs +5 -49
- data/ext/html-to-markdown-rb/native/src/conversion/mod.rs +0 -6
- data/ext/html-to-markdown-rb/native/src/lib.rs +76 -213
- data/ext/html-to-markdown-rb/native/src/options.rs +0 -3
- data/lib/html_to_markdown/version.rb +1 -1
- data/lib/html_to_markdown.rb +13 -194
- data/sig/html_to_markdown.rbs +12 -373
- data/vendor/Cargo.toml +6 -3
- data/vendor/html-to-markdown-rs/Cargo.toml +4 -10
- data/vendor/html-to-markdown-rs/README.md +126 -52
- data/vendor/html-to-markdown-rs/examples/basic.rs +6 -1
- data/vendor/html-to-markdown-rs/examples/table.rs +6 -1
- data/vendor/html-to-markdown-rs/examples/test_escape.rs +6 -1
- data/vendor/html-to-markdown-rs/examples/test_inline_formatting.rs +8 -2
- data/vendor/html-to-markdown-rs/examples/test_lists.rs +6 -1
- data/vendor/html-to-markdown-rs/examples/test_semantic_tags.rs +6 -1
- data/vendor/html-to-markdown-rs/examples/test_tables.rs +6 -1
- data/vendor/html-to-markdown-rs/examples/test_task_lists.rs +6 -1
- data/vendor/html-to-markdown-rs/examples/test_whitespace.rs +6 -1
- data/vendor/html-to-markdown-rs/src/convert_api.rs +151 -745
- data/vendor/html-to-markdown-rs/src/converter/block/blockquote.rs +3 -5
- data/vendor/html-to-markdown-rs/src/converter/block/div.rs +1 -7
- data/vendor/html-to-markdown-rs/src/converter/block/heading.rs +18 -5
- data/vendor/html-to-markdown-rs/src/converter/block/paragraph.rs +10 -0
- data/vendor/html-to-markdown-rs/src/converter/block/preformatted.rs +3 -5
- data/vendor/html-to-markdown-rs/src/converter/block/table/builder.rs +16 -11
- data/vendor/html-to-markdown-rs/src/converter/block/table/cell.rs +20 -0
- data/vendor/html-to-markdown-rs/src/converter/block/table/cells.rs +4 -17
- data/vendor/html-to-markdown-rs/src/converter/block/table/mod.rs +140 -0
- data/vendor/html-to-markdown-rs/src/converter/block/table/scanner.rs +4 -18
- data/vendor/html-to-markdown-rs/src/converter/block/table/utils.rs +2 -18
- data/vendor/html-to-markdown-rs/src/converter/context.rs +8 -0
- data/vendor/html-to-markdown-rs/src/converter/dom_context.rs +1 -6
- data/vendor/html-to-markdown-rs/src/converter/form/elements.rs +14 -14
- data/vendor/html-to-markdown-rs/src/converter/handlers/blockquote.rs +4 -5
- data/vendor/html-to-markdown-rs/src/converter/handlers/code_block.rs +5 -10
- data/vendor/html-to-markdown-rs/src/converter/handlers/graphic.rs +3 -5
- data/vendor/html-to-markdown-rs/src/converter/handlers/image.rs +3 -5
- data/vendor/html-to-markdown-rs/src/converter/handlers/link.rs +3 -5
- data/vendor/html-to-markdown-rs/src/converter/inline/code.rs +3 -5
- data/vendor/html-to-markdown-rs/src/converter/inline/emphasis.rs +4 -10
- data/vendor/html-to-markdown-rs/src/converter/inline/link.rs +4 -170
- data/vendor/html-to-markdown-rs/src/converter/inline/semantic/marks.rs +7 -19
- data/vendor/html-to-markdown-rs/src/converter/list/item.rs +3 -5
- data/vendor/html-to-markdown-rs/src/converter/list/ordered.rs +4 -10
- data/vendor/html-to-markdown-rs/src/converter/list/unordered.rs +6 -12
- data/vendor/html-to-markdown-rs/src/converter/list/utils.rs +1 -12
- data/vendor/html-to-markdown-rs/src/converter/main.rs +85 -56
- data/vendor/html-to-markdown-rs/src/converter/main_helpers.rs +4 -68
- data/vendor/html-to-markdown-rs/src/converter/media/embedded.rs +1 -5
- data/vendor/html-to-markdown-rs/src/converter/media/graphic.rs +3 -40
- data/vendor/html-to-markdown-rs/src/converter/media/image.rs +0 -8
- data/vendor/html-to-markdown-rs/src/converter/media/svg.rs +3 -13
- data/vendor/html-to-markdown-rs/src/converter/metadata.rs +1 -1
- data/vendor/html-to-markdown-rs/src/converter/mod.rs +0 -8
- data/vendor/html-to-markdown-rs/src/converter/plain_text.rs +37 -12
- data/vendor/html-to-markdown-rs/src/converter/semantic/attributes.rs +5 -30
- data/vendor/html-to-markdown-rs/src/converter/semantic/figure.rs +29 -0
- data/vendor/html-to-markdown-rs/src/converter/text/escaping.rs +1 -36
- data/vendor/html-to-markdown-rs/src/converter/text/mod.rs +1 -3
- data/vendor/html-to-markdown-rs/src/converter/text/normalization.rs +0 -53
- data/vendor/html-to-markdown-rs/src/converter/text_node.rs +1 -1
- data/vendor/html-to-markdown-rs/src/converter/utility/attributes.rs +0 -41
- data/vendor/html-to-markdown-rs/src/converter/utility/caching.rs +2 -1
- data/vendor/html-to-markdown-rs/src/converter/utility/content.rs +15 -98
- data/vendor/html-to-markdown-rs/src/converter/utility/preprocessing.rs +113 -4
- data/vendor/html-to-markdown-rs/src/converter/utility/serialization.rs +3 -0
- data/vendor/html-to-markdown-rs/src/converter/visitor_hooks.rs +4 -10
- data/vendor/html-to-markdown-rs/src/exports.rs +1 -4
- data/vendor/html-to-markdown-rs/src/inline_images.rs +1 -1
- data/vendor/html-to-markdown-rs/src/lib.rs +13 -133
- data/vendor/html-to-markdown-rs/src/metadata/collector.rs +4 -4
- data/vendor/html-to-markdown-rs/src/metadata/mod.rs +22 -22
- data/vendor/html-to-markdown-rs/src/metadata/types.rs +3 -3
- data/vendor/html-to-markdown-rs/src/options/conversion.rs +351 -323
- data/vendor/html-to-markdown-rs/src/options/preprocessing.rs +8 -2
- data/vendor/html-to-markdown-rs/src/prelude.rs +1 -15
- data/vendor/html-to-markdown-rs/src/rcdom.rs +7 -1
- data/vendor/html-to-markdown-rs/src/text.rs +25 -14
- data/vendor/html-to-markdown-rs/src/types/document.rs +175 -0
- data/vendor/html-to-markdown-rs/src/types/mod.rs +17 -0
- data/vendor/html-to-markdown-rs/src/types/result.rs +49 -0
- data/vendor/html-to-markdown-rs/src/types/structure_builder.rs +790 -0
- data/vendor/html-to-markdown-rs/src/types/structure_collector.rs +442 -0
- data/vendor/html-to-markdown-rs/src/types/tables.rs +47 -0
- data/vendor/html-to-markdown-rs/src/types/warnings.rs +28 -0
- data/vendor/html-to-markdown-rs/src/visitor/mod.rs +0 -6
- data/vendor/html-to-markdown-rs/src/visitor/traits.rs +0 -1
- data/vendor/html-to-markdown-rs/src/visitor_helpers/helpers/callbacks/mod.rs +1 -21
- data/vendor/html-to-markdown-rs/src/visitor_helpers/helpers/mod.rs +0 -5
- data/vendor/html-to-markdown-rs/src/visitor_helpers.rs +1 -845
- data/vendor/html-to-markdown-rs/tests/br_in_inline_test.rs +8 -1
- data/vendor/html-to-markdown-rs/tests/commonmark_compliance_test.rs +8 -8
- data/vendor/html-to-markdown-rs/tests/djot_output_test.rs +8 -2
- data/vendor/html-to-markdown-rs/tests/integration_test.rs +23 -6
- data/vendor/html-to-markdown-rs/tests/issue_121_regressions.rs +8 -1
- data/vendor/html-to-markdown-rs/tests/issue_127_regressions.rs +8 -2
- data/vendor/html-to-markdown-rs/tests/issue_128_regressions.rs +6 -1
- data/vendor/html-to-markdown-rs/tests/issue_131_regressions.rs +8 -1
- data/vendor/html-to-markdown-rs/tests/issue_134_regressions.rs +8 -1
- data/vendor/html-to-markdown-rs/tests/issue_139_regressions.rs +8 -1
- data/vendor/html-to-markdown-rs/tests/issue_140_regressions.rs +8 -1
- data/vendor/html-to-markdown-rs/tests/issue_143_regressions.rs +8 -1
- data/vendor/html-to-markdown-rs/tests/issue_145_regressions.rs +8 -7
- data/vendor/html-to-markdown-rs/tests/issue_146_regressions.rs +8 -7
- data/vendor/html-to-markdown-rs/tests/issue_176_regressions.rs +12 -2
- data/vendor/html-to-markdown-rs/tests/issue_190_regressions.rs +8 -1
- data/vendor/html-to-markdown-rs/tests/issue_199_regressions.rs +6 -1
- data/vendor/html-to-markdown-rs/tests/issue_200_regressions.rs +6 -1
- data/vendor/html-to-markdown-rs/tests/issue_212_regressions.rs +6 -1
- data/vendor/html-to-markdown-rs/tests/issue_216_217_regressions.rs +6 -1
- data/vendor/html-to-markdown-rs/tests/json_ld_script_extraction.rs +4 -6
- data/vendor/html-to-markdown-rs/tests/lists_test.rs +8 -1
- data/vendor/html-to-markdown-rs/tests/plain_output_test.rs +8 -2
- data/vendor/html-to-markdown-rs/tests/preprocessing_tests.rs +8 -1
- data/vendor/html-to-markdown-rs/tests/skip_images_test.rs +8 -11
- data/vendor/html-to-markdown-rs/tests/tables_test.rs +12 -2
- data/vendor/html-to-markdown-rs/tests/test_custom_elements.rs +8 -1
- data/vendor/html-to-markdown-rs/tests/test_nested_simple.rs +8 -1
- data/vendor/html-to-markdown-rs/tests/test_script_style_stripping.rs +17 -28
- data/vendor/html-to-markdown-rs/tests/test_spa_bisect.rs +8 -1
- data/vendor/html-to-markdown-rs/tests/visitor_integration_test.rs +29 -33
- data/vendor/html-to-markdown-rs/tests/xml_tables_test.rs +8 -1
- metadata +9 -37
- data/bin/benchmark.rb +0 -232
- data/ext/html-to-markdown-rb/native/src/conversion/tables.rs +0 -71
- data/ext/html-to-markdown-rb/native/src/profiling.rs +0 -215
- data/ext/html-to-markdown-rb/native/src/visitor/bridge.rs +0 -252
- data/ext/html-to-markdown-rb/native/src/visitor/callbacks.rs +0 -640
- data/ext/html-to-markdown-rb/native/src/visitor/mod.rs +0 -12
- data/spec/convert_spec.rb +0 -77
- data/spec/convert_with_tables_spec.rb +0 -194
- data/spec/metadata_extraction_spec.rb +0 -437
- data/spec/visitor_issue_187_spec.rb +0 -605
- data/spec/visitor_spec.rb +0 -1149
- data/vendor/html-to-markdown-rs/src/hocr/converter/code_analysis.rs +0 -254
- data/vendor/html-to-markdown-rs/src/hocr/converter/core.rs +0 -249
- data/vendor/html-to-markdown-rs/src/hocr/converter/elements.rs +0 -382
- data/vendor/html-to-markdown-rs/src/hocr/converter/hierarchy.rs +0 -379
- data/vendor/html-to-markdown-rs/src/hocr/converter/keywords.rs +0 -55
- data/vendor/html-to-markdown-rs/src/hocr/converter/layout.rs +0 -313
- data/vendor/html-to-markdown-rs/src/hocr/converter/mod.rs +0 -26
- data/vendor/html-to-markdown-rs/src/hocr/converter/output.rs +0 -78
- data/vendor/html-to-markdown-rs/src/hocr/extractor.rs +0 -232
- data/vendor/html-to-markdown-rs/src/hocr/mod.rs +0 -42
- data/vendor/html-to-markdown-rs/src/hocr/parser.rs +0 -333
- data/vendor/html-to-markdown-rs/src/hocr/spatial/coords.rs +0 -129
- data/vendor/html-to-markdown-rs/src/hocr/spatial/grouping.rs +0 -165
- data/vendor/html-to-markdown-rs/src/hocr/spatial/layout.rs +0 -335
- data/vendor/html-to-markdown-rs/src/hocr/spatial/mod.rs +0 -15
- data/vendor/html-to-markdown-rs/src/hocr/spatial/output.rs +0 -63
- data/vendor/html-to-markdown-rs/src/hocr/types.rs +0 -269
- data/vendor/html-to-markdown-rs/src/visitor/async_traits.rs +0 -249
- data/vendor/html-to-markdown-rs/src/visitor_helpers/helpers/callbacks/bridge.rs +0 -189
- data/vendor/html-to-markdown-rs/src/visitor_helpers/helpers/callbacks/bridge_visitor.rs +0 -343
- data/vendor/html-to-markdown-rs/src/visitor_helpers/helpers/callbacks/macros.rs +0 -217
- data/vendor/html-to-markdown-rs/tests/async_visitor_test.rs +0 -57
- data/vendor/html-to-markdown-rs/tests/convert_with_metadata_no_frontmatter.rs +0 -100
- data/vendor/html-to-markdown-rs/tests/hocr_compliance_test.rs +0 -509
|
@@ -1,215 +0,0 @@
|
|
|
1
|
-
use html_to_markdown_rs::{ConversionError, Result};
|
|
2
|
-
use std::path::PathBuf;
|
|
3
|
-
|
|
4
|
-
#[cfg(all(not(target_os = "windows"), feature = "profiling"))]
|
|
5
|
-
mod enabled {
|
|
6
|
-
use super::{ConversionError, PathBuf, Result};
|
|
7
|
-
use std::sync::atomic::{AtomicBool, Ordering};
|
|
8
|
-
use std::sync::{Mutex, OnceLock};
|
|
9
|
-
|
|
10
|
-
const ENV_OUTPUT: &str = "HTML_TO_MARKDOWN_PROFILE_OUTPUT";
|
|
11
|
-
const ENV_FREQUENCY: &str = "HTML_TO_MARKDOWN_PROFILE_FREQUENCY";
|
|
12
|
-
const ENV_ONCE: &str = "HTML_TO_MARKDOWN_PROFILE_ONCE";
|
|
13
|
-
|
|
14
|
-
static PROFILED_ONCE: AtomicBool = AtomicBool::new(false);
|
|
15
|
-
static PROFILE_ACTIVE: AtomicBool = AtomicBool::new(false);
|
|
16
|
-
|
|
17
|
-
struct EnvProfileConfig {
|
|
18
|
-
output: Option<PathBuf>,
|
|
19
|
-
profile_once: bool,
|
|
20
|
-
frequency: i32,
|
|
21
|
-
}
|
|
22
|
-
|
|
23
|
-
fn env_profile_config() -> &'static EnvProfileConfig {
|
|
24
|
-
static ENV_CONFIG: OnceLock<EnvProfileConfig> = OnceLock::new();
|
|
25
|
-
ENV_CONFIG.get_or_init(|| {
|
|
26
|
-
let output = match std::env::var(ENV_OUTPUT) {
|
|
27
|
-
Ok(value) if !value.trim().is_empty() => Some(PathBuf::from(value)),
|
|
28
|
-
_ => None,
|
|
29
|
-
};
|
|
30
|
-
|
|
31
|
-
let profile_once = match std::env::var(ENV_ONCE) {
|
|
32
|
-
Ok(value) => !matches!(value.as_str(), "0" | "false" | "no"),
|
|
33
|
-
Err(_) => true,
|
|
34
|
-
};
|
|
35
|
-
|
|
36
|
-
let frequency = std::env::var(ENV_FREQUENCY)
|
|
37
|
-
.ok()
|
|
38
|
-
.and_then(|value| value.parse::<i32>().ok())
|
|
39
|
-
.unwrap_or(1000);
|
|
40
|
-
|
|
41
|
-
EnvProfileConfig {
|
|
42
|
-
output,
|
|
43
|
-
profile_once,
|
|
44
|
-
frequency,
|
|
45
|
-
}
|
|
46
|
-
})
|
|
47
|
-
}
|
|
48
|
-
|
|
49
|
-
struct ProfileState {
|
|
50
|
-
guard: Option<pprof::ProfilerGuard<'static>>,
|
|
51
|
-
output: Option<PathBuf>,
|
|
52
|
-
}
|
|
53
|
-
|
|
54
|
-
fn state() -> &'static Mutex<ProfileState> {
|
|
55
|
-
static STATE: OnceLock<Mutex<ProfileState>> = OnceLock::new();
|
|
56
|
-
STATE.get_or_init(|| {
|
|
57
|
-
Mutex::new(ProfileState {
|
|
58
|
-
guard: None,
|
|
59
|
-
output: None,
|
|
60
|
-
})
|
|
61
|
-
})
|
|
62
|
-
}
|
|
63
|
-
|
|
64
|
-
pub fn start(output_path: PathBuf, frequency: i32) -> Result<()> {
|
|
65
|
-
let mut state = state()
|
|
66
|
-
.lock()
|
|
67
|
-
.map_err(|_| ConversionError::Other("profiling state lock poisoned".to_string()))?;
|
|
68
|
-
|
|
69
|
-
if state.guard.is_some() {
|
|
70
|
-
return Err(ConversionError::Other("profiling already active".to_string()));
|
|
71
|
-
}
|
|
72
|
-
|
|
73
|
-
let guard = pprof::ProfilerGuardBuilder::default()
|
|
74
|
-
.frequency(frequency)
|
|
75
|
-
.blocklist(&["libc", "libpthread", "libgcc", "libm"])
|
|
76
|
-
.build()
|
|
77
|
-
.map_err(|err| ConversionError::Other(format!("Profiling init failed: {err}")))?;
|
|
78
|
-
|
|
79
|
-
state.guard = Some(guard);
|
|
80
|
-
state.output = Some(output_path);
|
|
81
|
-
PROFILE_ACTIVE.store(true, Ordering::Release);
|
|
82
|
-
Ok(())
|
|
83
|
-
}
|
|
84
|
-
|
|
85
|
-
pub fn stop() -> Result<()> {
|
|
86
|
-
let (guard, output) = {
|
|
87
|
-
let mut state = state()
|
|
88
|
-
.lock()
|
|
89
|
-
.map_err(|_| ConversionError::Other("profiling state lock poisoned".to_string()))?;
|
|
90
|
-
let guard = state.guard.take();
|
|
91
|
-
let output = state.output.take();
|
|
92
|
-
(guard, output)
|
|
93
|
-
};
|
|
94
|
-
PROFILE_ACTIVE.store(false, Ordering::Release);
|
|
95
|
-
|
|
96
|
-
let Some(guard) = guard else {
|
|
97
|
-
return Err(ConversionError::Other("profiling not active".to_string()));
|
|
98
|
-
};
|
|
99
|
-
let Some(output_path) = output else {
|
|
100
|
-
return Err(ConversionError::Other("profiling output path missing".to_string()));
|
|
101
|
-
};
|
|
102
|
-
|
|
103
|
-
if let Some(parent) = output_path.parent() {
|
|
104
|
-
std::fs::create_dir_all(parent).map_err(ConversionError::IoError)?;
|
|
105
|
-
}
|
|
106
|
-
|
|
107
|
-
let report = guard
|
|
108
|
-
.report()
|
|
109
|
-
.build()
|
|
110
|
-
.map_err(|err| ConversionError::Other(format!("Profiling report failed: {err}")))?;
|
|
111
|
-
|
|
112
|
-
let file = std::fs::File::create(&output_path).map_err(ConversionError::IoError)?;
|
|
113
|
-
report
|
|
114
|
-
.flamegraph(file)
|
|
115
|
-
.map_err(|err| ConversionError::Other(format!("Flamegraph write failed: {err}")))?;
|
|
116
|
-
PROFILE_ACTIVE.store(false, Ordering::Release);
|
|
117
|
-
Ok(())
|
|
118
|
-
}
|
|
119
|
-
|
|
120
|
-
pub fn maybe_profile<T, F>(f: F) -> Result<T>
|
|
121
|
-
where
|
|
122
|
-
F: FnOnce() -> Result<T>,
|
|
123
|
-
{
|
|
124
|
-
if PROFILE_ACTIVE.load(Ordering::Relaxed) {
|
|
125
|
-
return f();
|
|
126
|
-
}
|
|
127
|
-
|
|
128
|
-
let config = env_profile_config();
|
|
129
|
-
let Some(output_path) = config.output.as_ref() else {
|
|
130
|
-
return f();
|
|
131
|
-
};
|
|
132
|
-
|
|
133
|
-
if config.profile_once && PROFILED_ONCE.swap(true, Ordering::SeqCst) {
|
|
134
|
-
return f();
|
|
135
|
-
}
|
|
136
|
-
|
|
137
|
-
struct ActiveGuard;
|
|
138
|
-
impl Drop for ActiveGuard {
|
|
139
|
-
fn drop(&mut self) {
|
|
140
|
-
PROFILE_ACTIVE.store(false, Ordering::Release);
|
|
141
|
-
}
|
|
142
|
-
}
|
|
143
|
-
PROFILE_ACTIVE.store(true, Ordering::Release);
|
|
144
|
-
let _active = ActiveGuard;
|
|
145
|
-
|
|
146
|
-
let guard = pprof::ProfilerGuardBuilder::default()
|
|
147
|
-
.frequency(config.frequency)
|
|
148
|
-
.blocklist(&["libc", "libpthread", "libgcc", "libm"])
|
|
149
|
-
.build()
|
|
150
|
-
.map_err(|err| ConversionError::Other(format!("Profiling init failed: {err}")))?;
|
|
151
|
-
|
|
152
|
-
let result = f();
|
|
153
|
-
|
|
154
|
-
if result.is_ok() {
|
|
155
|
-
if let Some(parent) = output_path.parent() {
|
|
156
|
-
std::fs::create_dir_all(parent).map_err(ConversionError::IoError)?;
|
|
157
|
-
}
|
|
158
|
-
|
|
159
|
-
let report = guard
|
|
160
|
-
.report()
|
|
161
|
-
.build()
|
|
162
|
-
.map_err(|err| ConversionError::Other(format!("Profiling report failed: {err}")))?;
|
|
163
|
-
|
|
164
|
-
let file = std::fs::File::create(output_path).map_err(ConversionError::IoError)?;
|
|
165
|
-
report
|
|
166
|
-
.flamegraph(file)
|
|
167
|
-
.map_err(|err| ConversionError::Other(format!("Flamegraph write failed: {err}")))?;
|
|
168
|
-
}
|
|
169
|
-
|
|
170
|
-
result
|
|
171
|
-
}
|
|
172
|
-
}
|
|
173
|
-
|
|
174
|
-
#[cfg(all(not(target_os = "windows"), feature = "profiling"))]
|
|
175
|
-
pub use enabled::{maybe_profile, start, stop};
|
|
176
|
-
|
|
177
|
-
#[cfg(target_os = "windows")]
|
|
178
|
-
#[allow(dead_code)]
|
|
179
|
-
pub fn start(_output_path: PathBuf, _frequency: i32) -> Result<()> {
|
|
180
|
-
Err(ConversionError::Other(
|
|
181
|
-
"Profiling is not supported on Windows".to_string(),
|
|
182
|
-
))
|
|
183
|
-
}
|
|
184
|
-
|
|
185
|
-
#[cfg(all(not(target_os = "windows"), not(feature = "profiling")))]
|
|
186
|
-
#[allow(dead_code)]
|
|
187
|
-
pub fn start(_output_path: PathBuf, _frequency: i32) -> Result<()> {
|
|
188
|
-
Err(ConversionError::Other(
|
|
189
|
-
"Profiling is disabled; rebuild with the profiling feature".to_string(),
|
|
190
|
-
))
|
|
191
|
-
}
|
|
192
|
-
|
|
193
|
-
#[cfg(target_os = "windows")]
|
|
194
|
-
#[allow(dead_code)]
|
|
195
|
-
pub fn stop() -> Result<()> {
|
|
196
|
-
Err(ConversionError::Other(
|
|
197
|
-
"Profiling is not supported on Windows".to_string(),
|
|
198
|
-
))
|
|
199
|
-
}
|
|
200
|
-
|
|
201
|
-
#[cfg(all(not(target_os = "windows"), not(feature = "profiling")))]
|
|
202
|
-
#[allow(dead_code)]
|
|
203
|
-
pub fn stop() -> Result<()> {
|
|
204
|
-
Err(ConversionError::Other(
|
|
205
|
-
"Profiling is disabled; rebuild with the profiling feature".to_string(),
|
|
206
|
-
))
|
|
207
|
-
}
|
|
208
|
-
|
|
209
|
-
#[cfg(any(target_os = "windows", not(feature = "profiling")))]
|
|
210
|
-
pub fn maybe_profile<T, F>(f: F) -> Result<T>
|
|
211
|
-
where
|
|
212
|
-
F: FnOnce() -> Result<T>,
|
|
213
|
-
{
|
|
214
|
-
f()
|
|
215
|
-
}
|
|
@@ -1,252 +0,0 @@
|
|
|
1
|
-
//! Ruby visitor wrapper and bridge utilities.
|
|
2
|
-
|
|
3
|
-
use crate::types::{arg_error, symbol_to_string};
|
|
4
|
-
use html_to_markdown_rs::visitor::{NodeContext, NodeType, VisitResult};
|
|
5
|
-
use magnus::prelude::*;
|
|
6
|
-
use magnus::{Error, RHash, Ruby, TryConvert, Value};
|
|
7
|
-
|
|
8
|
-
/// Wrapper for a Ruby visitor object that implements the HtmlVisitor trait.
|
|
9
|
-
#[derive(Clone)]
|
|
10
|
-
pub struct RubyVisitorWrapper {
|
|
11
|
-
pub ruby_visitor: Value,
|
|
12
|
-
pub last_error: std::rc::Rc<std::cell::RefCell<Option<String>>>,
|
|
13
|
-
}
|
|
14
|
-
|
|
15
|
-
impl RubyVisitorWrapper {
|
|
16
|
-
pub fn new(ruby_visitor: Value) -> Self {
|
|
17
|
-
Self {
|
|
18
|
-
ruby_visitor,
|
|
19
|
-
last_error: std::rc::Rc::new(std::cell::RefCell::new(None)),
|
|
20
|
-
}
|
|
21
|
-
}
|
|
22
|
-
|
|
23
|
-
pub fn utf8_str(&self, ruby: &Ruby, s: &str) -> Value {
|
|
24
|
-
if let Ok(val) = ruby.eval::<Value>(&format!("String.new({s:?}, encoding: 'UTF-8')")) {
|
|
25
|
-
val
|
|
26
|
-
} else {
|
|
27
|
-
let str_val = ruby.str_from_slice(s.as_bytes());
|
|
28
|
-
str_val.as_value()
|
|
29
|
-
}
|
|
30
|
-
}
|
|
31
|
-
|
|
32
|
-
pub fn call_visitor_method(&self, method_name: &str, args: &[Value]) -> Result<VisitResult, Error> {
|
|
33
|
-
let ruby = Ruby::get().expect("Ruby not initialized");
|
|
34
|
-
|
|
35
|
-
let result: Value = match args.len() {
|
|
36
|
-
0 => match self.ruby_visitor.funcall::<&str, (), Value>(method_name, ()) {
|
|
37
|
-
Ok(val) => val,
|
|
38
|
-
Err(e) => {
|
|
39
|
-
*self.last_error.borrow_mut() = Some(format!("Visitor error in {method_name}: {e}"));
|
|
40
|
-
return Err(e);
|
|
41
|
-
}
|
|
42
|
-
},
|
|
43
|
-
1 => match self
|
|
44
|
-
.ruby_visitor
|
|
45
|
-
.funcall::<&str, (Value,), Value>(method_name, (args[0],))
|
|
46
|
-
{
|
|
47
|
-
Ok(val) => val,
|
|
48
|
-
Err(e) => {
|
|
49
|
-
*self.last_error.borrow_mut() = Some(format!("Visitor error in {method_name}: {e}"));
|
|
50
|
-
return Err(e);
|
|
51
|
-
}
|
|
52
|
-
},
|
|
53
|
-
2 => match self
|
|
54
|
-
.ruby_visitor
|
|
55
|
-
.funcall::<&str, (Value, Value), Value>(method_name, (args[0], args[1]))
|
|
56
|
-
{
|
|
57
|
-
Ok(val) => val,
|
|
58
|
-
Err(e) => {
|
|
59
|
-
*self.last_error.borrow_mut() = Some(format!("Visitor error in {method_name}: {e}"));
|
|
60
|
-
return Err(e);
|
|
61
|
-
}
|
|
62
|
-
},
|
|
63
|
-
3 => match self
|
|
64
|
-
.ruby_visitor
|
|
65
|
-
.funcall::<&str, (Value, Value, Value), Value>(method_name, (args[0], args[1], args[2]))
|
|
66
|
-
{
|
|
67
|
-
Ok(val) => val,
|
|
68
|
-
Err(e) => {
|
|
69
|
-
*self.last_error.borrow_mut() = Some(format!("Visitor error in {method_name}: {e}"));
|
|
70
|
-
return Err(e);
|
|
71
|
-
}
|
|
72
|
-
},
|
|
73
|
-
4 => match self
|
|
74
|
-
.ruby_visitor
|
|
75
|
-
.funcall::<&str, (Value, Value, Value, Value), Value>(method_name, (args[0], args[1], args[2], args[3]))
|
|
76
|
-
{
|
|
77
|
-
Ok(val) => val,
|
|
78
|
-
Err(e) => {
|
|
79
|
-
*self.last_error.borrow_mut() = Some(format!("Visitor error in {method_name}: {e}"));
|
|
80
|
-
return Err(e);
|
|
81
|
-
}
|
|
82
|
-
},
|
|
83
|
-
_ => {
|
|
84
|
-
return Err(arg_error(format!(
|
|
85
|
-
"Unsupported number of visitor method arguments: {}",
|
|
86
|
-
args.len()
|
|
87
|
-
)));
|
|
88
|
-
}
|
|
89
|
-
};
|
|
90
|
-
|
|
91
|
-
let hash = RHash::from_value(result)
|
|
92
|
-
.ok_or_else(|| arg_error(format!("visitor method {method_name} must return a Hash")))?;
|
|
93
|
-
|
|
94
|
-
let type_value: Value = hash
|
|
95
|
-
.get(ruby.intern("type"))
|
|
96
|
-
.ok_or_else(|| arg_error(format!("visitor method {method_name} result Hash must have :type key")))?;
|
|
97
|
-
|
|
98
|
-
let type_str = symbol_to_string(type_value)?;
|
|
99
|
-
|
|
100
|
-
match type_str.as_str() {
|
|
101
|
-
"continue" => Ok(VisitResult::Continue),
|
|
102
|
-
"custom" => {
|
|
103
|
-
let output_value: Value = hash.get(ruby.intern("output")).ok_or_else(|| {
|
|
104
|
-
arg_error(format!(
|
|
105
|
-
"visitor method {method_name} with type :custom must provide :output string"
|
|
106
|
-
))
|
|
107
|
-
})?;
|
|
108
|
-
let output = String::try_convert(output_value)?;
|
|
109
|
-
Ok(VisitResult::Custom(output))
|
|
110
|
-
}
|
|
111
|
-
"skip" => Ok(VisitResult::Skip),
|
|
112
|
-
"preserve_html" => Ok(VisitResult::PreserveHtml),
|
|
113
|
-
"error" => {
|
|
114
|
-
let message_value: Value = hash.get(ruby.intern("message")).ok_or_else(|| {
|
|
115
|
-
arg_error(format!(
|
|
116
|
-
"visitor method {method_name} with type :error must provide :message string"
|
|
117
|
-
))
|
|
118
|
-
})?;
|
|
119
|
-
let message = String::try_convert(message_value)?;
|
|
120
|
-
Ok(VisitResult::Error(message))
|
|
121
|
-
}
|
|
122
|
-
other => Err(arg_error(format!(
|
|
123
|
-
"visitor method {method_name} returned invalid type: {other}"
|
|
124
|
-
))),
|
|
125
|
-
}
|
|
126
|
-
}
|
|
127
|
-
|
|
128
|
-
pub fn ruby_to_node_context(&self, ctx: &NodeContext, ruby: &Ruby) -> Result<Value, Error> {
|
|
129
|
-
let hash = ruby.hash_new();
|
|
130
|
-
|
|
131
|
-
let node_type_str = match ctx.node_type {
|
|
132
|
-
NodeType::Text => "text",
|
|
133
|
-
NodeType::Element => "element",
|
|
134
|
-
NodeType::Heading => "heading",
|
|
135
|
-
NodeType::Paragraph => "paragraph",
|
|
136
|
-
NodeType::Div => "div",
|
|
137
|
-
NodeType::Blockquote => "blockquote",
|
|
138
|
-
NodeType::Pre => "pre",
|
|
139
|
-
NodeType::Hr => "hr",
|
|
140
|
-
NodeType::List => "list",
|
|
141
|
-
NodeType::ListItem => "list_item",
|
|
142
|
-
NodeType::DefinitionList => "definition_list",
|
|
143
|
-
NodeType::DefinitionTerm => "definition_term",
|
|
144
|
-
NodeType::DefinitionDescription => "definition_description",
|
|
145
|
-
NodeType::Table => "table",
|
|
146
|
-
NodeType::TableRow => "table_row",
|
|
147
|
-
NodeType::TableCell => "table_cell",
|
|
148
|
-
NodeType::TableHeader => "table_header",
|
|
149
|
-
NodeType::TableBody => "table_body",
|
|
150
|
-
NodeType::TableHead => "table_head",
|
|
151
|
-
NodeType::TableFoot => "table_foot",
|
|
152
|
-
NodeType::Link => "link",
|
|
153
|
-
NodeType::Image => "image",
|
|
154
|
-
NodeType::Strong => "strong",
|
|
155
|
-
NodeType::Em => "em",
|
|
156
|
-
NodeType::Code => "code",
|
|
157
|
-
NodeType::Strikethrough => "strikethrough",
|
|
158
|
-
NodeType::Underline => "underline",
|
|
159
|
-
NodeType::Subscript => "subscript",
|
|
160
|
-
NodeType::Superscript => "superscript",
|
|
161
|
-
NodeType::Mark => "mark",
|
|
162
|
-
NodeType::Small => "small",
|
|
163
|
-
NodeType::Br => "br",
|
|
164
|
-
NodeType::Span => "span",
|
|
165
|
-
NodeType::Article => "article",
|
|
166
|
-
NodeType::Section => "section",
|
|
167
|
-
NodeType::Nav => "nav",
|
|
168
|
-
NodeType::Aside => "aside",
|
|
169
|
-
NodeType::Header => "header",
|
|
170
|
-
NodeType::Footer => "footer",
|
|
171
|
-
NodeType::Main => "main",
|
|
172
|
-
NodeType::Figure => "figure",
|
|
173
|
-
NodeType::Figcaption => "figcaption",
|
|
174
|
-
NodeType::Time => "time",
|
|
175
|
-
NodeType::Details => "details",
|
|
176
|
-
NodeType::Summary => "summary",
|
|
177
|
-
NodeType::Form => "form",
|
|
178
|
-
NodeType::Input => "input",
|
|
179
|
-
NodeType::Select => "select",
|
|
180
|
-
NodeType::Option => "option",
|
|
181
|
-
NodeType::Button => "button",
|
|
182
|
-
NodeType::Textarea => "textarea",
|
|
183
|
-
NodeType::Label => "label",
|
|
184
|
-
NodeType::Fieldset => "fieldset",
|
|
185
|
-
NodeType::Legend => "legend",
|
|
186
|
-
NodeType::Audio => "audio",
|
|
187
|
-
NodeType::Video => "video",
|
|
188
|
-
NodeType::Picture => "picture",
|
|
189
|
-
NodeType::Source => "source",
|
|
190
|
-
NodeType::Iframe => "iframe",
|
|
191
|
-
NodeType::Svg => "svg",
|
|
192
|
-
NodeType::Canvas => "canvas",
|
|
193
|
-
NodeType::Ruby => "ruby",
|
|
194
|
-
NodeType::Rt => "rt",
|
|
195
|
-
NodeType::Rp => "rp",
|
|
196
|
-
NodeType::Abbr => "abbr",
|
|
197
|
-
NodeType::Kbd => "kbd",
|
|
198
|
-
NodeType::Samp => "samp",
|
|
199
|
-
NodeType::Var => "var",
|
|
200
|
-
NodeType::Cite => "cite",
|
|
201
|
-
NodeType::Q => "q",
|
|
202
|
-
NodeType::Del => "del",
|
|
203
|
-
NodeType::Ins => "ins",
|
|
204
|
-
NodeType::Data => "data",
|
|
205
|
-
NodeType::Meter => "meter",
|
|
206
|
-
NodeType::Progress => "progress",
|
|
207
|
-
NodeType::Output => "output",
|
|
208
|
-
NodeType::Template => "template",
|
|
209
|
-
NodeType::Slot => "slot",
|
|
210
|
-
NodeType::Html => "html",
|
|
211
|
-
NodeType::Head => "head",
|
|
212
|
-
NodeType::Body => "body",
|
|
213
|
-
NodeType::Title => "title",
|
|
214
|
-
NodeType::Meta => "meta",
|
|
215
|
-
NodeType::LinkTag => "link_tag",
|
|
216
|
-
NodeType::Style => "style",
|
|
217
|
-
NodeType::Script => "script",
|
|
218
|
-
NodeType::Base => "base",
|
|
219
|
-
NodeType::Custom => "custom",
|
|
220
|
-
};
|
|
221
|
-
hash.aset(ruby.intern("node_type"), ruby.intern(node_type_str))?;
|
|
222
|
-
|
|
223
|
-
hash.aset(ruby.intern("tag_name"), ctx.tag_name.as_str())?;
|
|
224
|
-
|
|
225
|
-
let attrs_hash = ruby.hash_new();
|
|
226
|
-
for (key, value) in &ctx.attributes {
|
|
227
|
-
attrs_hash.aset(key.as_str(), value.as_str())?;
|
|
228
|
-
}
|
|
229
|
-
hash.aset(ruby.intern("attributes"), attrs_hash)?;
|
|
230
|
-
|
|
231
|
-
hash.aset(ruby.intern("depth"), ctx.depth as i64)?;
|
|
232
|
-
|
|
233
|
-
hash.aset(ruby.intern("index_in_parent"), ctx.index_in_parent as i64)?;
|
|
234
|
-
|
|
235
|
-
match &ctx.parent_tag {
|
|
236
|
-
Some(tag) => hash.aset(ruby.intern("parent_tag"), tag.as_str())?,
|
|
237
|
-
None => hash.aset(ruby.intern("parent_tag"), ruby.qnil())?,
|
|
238
|
-
}
|
|
239
|
-
|
|
240
|
-
hash.aset(ruby.intern("is_inline"), ctx.is_inline)?;
|
|
241
|
-
|
|
242
|
-
Ok(hash.as_value())
|
|
243
|
-
}
|
|
244
|
-
}
|
|
245
|
-
|
|
246
|
-
impl std::fmt::Debug for RubyVisitorWrapper {
|
|
247
|
-
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
|
248
|
-
f.debug_struct("RubyVisitorWrapper")
|
|
249
|
-
.field("ruby_visitor", &self.ruby_visitor)
|
|
250
|
-
.finish()
|
|
251
|
-
}
|
|
252
|
-
}
|