Add snapshot tests for html output
- Article contents are from the 2023-04-01 Wikipedia Enterprise Dump - Add benchmark for HTML processing Signed-off-by: Evan Lloyd New-Schmidt <evan@new-schmidt.com>
This commit is contained in:
Evan Lloyd New-Schmidt
Evan Lloyd New-Schmidt
parent
32cd084f3f
commit
75fa04407d
11 changed files with 1074 additions and 5 deletions
19
Cargo.lock
generated
19
Cargo.lock
generated
|
|
@ -314,6 +314,12 @@ dependencies = [
|
|||
"syn 1.0.109",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "dissimilar"
|
||||
version = "1.0.7"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "86e3bdc80eee6e16b2b6b0f87fbc98c04bee3455e35174c0de1a125d0688c632"
|
||||
|
||||
[[package]]
|
||||
name = "dtoa"
|
||||
version = "0.4.8"
|
||||
|
|
@ -375,6 +381,16 @@ dependencies = [
|
|||
"libc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "expect-test"
|
||||
version = "1.4.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "30d9eafeadd538e68fb28016364c9732d78e420b9ff8853fa5e4058861e9f8d3"
|
||||
dependencies = [
|
||||
"dissimilar",
|
||||
"once_cell",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "fastrand"
|
||||
version = "2.0.0"
|
||||
|
|
@ -685,7 +701,10 @@ dependencies = [
|
|||
"csv",
|
||||
"ego-tree",
|
||||
"env_logger",
|
||||
"expect-test",
|
||||
"html5ever",
|
||||
"log",
|
||||
"markup5ever",
|
||||
"once_cell",
|
||||
"osmpbf",
|
||||
"rayon",
|
||||
|
|
|
|||
|
|
@ -13,7 +13,10 @@ clap = { version = "4.3.2", features = ["derive"] }
|
|||
csv = "1.2.2"
|
||||
ego-tree = "0.6.2"
|
||||
env_logger = "0.10.0"
|
||||
expect-test = "1.4.1"
|
||||
html5ever = "0.26.0"
|
||||
log = "0.4.18"
|
||||
markup5ever = "0.11.0"
|
||||
once_cell = "1.18.0"
|
||||
osmpbf = "0.3.1"
|
||||
rayon = "1.7.0"
|
||||
|
|
|
|||
20
benches/html_processing.rs
Normal file
20
benches/html_processing.rs
Normal file
|
|
@ -0,0 +1,20 @@
|
|||
#![feature(test)]
|
||||
|
||||
extern crate om_wikiparser;
|
||||
extern crate test;
|
||||
|
||||
use test::{bench::black_box, Bencher};
|
||||
|
||||
use om_wikiparser::html;
|
||||
|
||||
#[bench]
|
||||
fn process_crimean_mountains(b: &mut Bencher) {
|
||||
let text = include_str!("../tests/data/Q4185820-en/original.html");
|
||||
|
||||
// process lazy statics beforehand
|
||||
black_box(html::simplify(text, "en"));
|
||||
|
||||
b.iter(|| {
|
||||
black_box(html::simplify(text, "en"));
|
||||
});
|
||||
}
|
||||
15
src/html.rs
15
src/html.rs
|
|
@ -5,6 +5,9 @@ use once_cell::sync::Lazy;
|
|||
use scraper::{ElementRef, Html, Selector};
|
||||
use serde::Deserialize;
|
||||
|
||||
mod pretty;
|
||||
pub use pretty::pretty_print;
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
struct Config<'a> {
|
||||
#[serde(borrow)]
|
||||
|
|
@ -37,7 +40,11 @@ static ELEMENT_ALLOW_LIST: Lazy<Selector> = Lazy::new(|| {
|
|||
|
||||
pub fn simplify(html: &str, lang: &str) -> String {
|
||||
let mut document = Html::parse_document(html);
|
||||
simplify_html(&mut document, lang);
|
||||
document.html()
|
||||
}
|
||||
|
||||
pub fn simplify_html(document: &mut Html, lang: &str) {
|
||||
let mut to_remove = Vec::new();
|
||||
|
||||
// Remove configured sections and all trailing elements until next section.
|
||||
|
|
@ -67,7 +74,7 @@ pub fn simplify(html: &str, lang: &str) -> String {
|
|||
}
|
||||
}
|
||||
|
||||
remove_ids(&mut document, to_remove.drain(..));
|
||||
remove_ids(document, to_remove.drain(..));
|
||||
}
|
||||
|
||||
for el in document
|
||||
|
|
@ -79,11 +86,9 @@ pub fn simplify(html: &str, lang: &str) -> String {
|
|||
to_remove.push(el.id());
|
||||
}
|
||||
}
|
||||
remove_ids(&mut document, to_remove.drain(..));
|
||||
remove_ids(document, to_remove.drain(..));
|
||||
|
||||
remove_links(&mut document);
|
||||
|
||||
document.html()
|
||||
remove_links(document);
|
||||
}
|
||||
|
||||
fn remove_ids(document: &mut Html, ids: impl IntoIterator<Item = NodeId>) {
|
||||
|
|
|
|||
128
src/html/pretty.rs
Normal file
128
src/html/pretty.rs
Normal file
|
|
@ -0,0 +1,128 @@
|
|||
// Based on the implementation from `htmlq`: https://github.com/mgdm/htmlq/blob/6e31bc814332b2521f0316d0ed9bf0a1c521b6e6/src/pretty_print.rs
|
||||
// Available under the MIT License.
|
||||
// Copyright (c) 2019 Michael Maclean
|
||||
|
||||
use std::{
|
||||
collections::HashSet,
|
||||
io::{self, Write},
|
||||
str,
|
||||
};
|
||||
|
||||
use html5ever::{
|
||||
serialize::{HtmlSerializer, Serialize, SerializeOpts, Serializer, TraversalScope},
|
||||
QualName,
|
||||
};
|
||||
|
||||
use markup5ever::serialize::AttrRef;
|
||||
use once_cell::sync::Lazy;
|
||||
use scraper::Html;
|
||||
|
||||
pub fn pretty_print(html: &Html) -> String {
|
||||
let mut content: Vec<u8> = Vec::new();
|
||||
let mut pp = PrettyPrint {
|
||||
indent: 0,
|
||||
previous_was_block: false,
|
||||
inner: HtmlSerializer::new(
|
||||
&mut content,
|
||||
SerializeOpts {
|
||||
traversal_scope: TraversalScope::IncludeNode,
|
||||
..Default::default()
|
||||
},
|
||||
),
|
||||
at_beginning: true,
|
||||
};
|
||||
Serialize::serialize(html, &mut pp, TraversalScope::IncludeNode).unwrap();
|
||||
str::from_utf8(content.as_ref()).unwrap().to_owned()
|
||||
}
|
||||
|
||||
/// Elements to print on a single line instead of expanded.
|
||||
static INLINE_ELEMENTS: Lazy<HashSet<&'static str>> = Lazy::new(|| {
|
||||
vec![
|
||||
"a", "abbr", "acronym", "audio", "b", "bdi", "bdo", "big", "button", "canvas", "cite",
|
||||
"code", "data", "datalist", "del", "dfn", "em", "embed", "i", "iframe", "img", "input",
|
||||
"ins", "kbd", "label", "map", "mark", "meter", "noscript", "object", "output", "picture",
|
||||
"progress", "q", "ruby", "s", "samp", "script", "select", "slot", "small", "span",
|
||||
"strong", "sub", "sup", "svg", "template", "textarea", "time", "u", "tt", "var", "video",
|
||||
"wbr",
|
||||
]
|
||||
.into_iter()
|
||||
.collect()
|
||||
});
|
||||
|
||||
fn is_inline(name: &str) -> bool {
|
||||
INLINE_ELEMENTS.contains(name)
|
||||
}
|
||||
|
||||
struct PrettyPrint<W: Write> {
|
||||
indent: usize,
|
||||
previous_was_block: bool,
|
||||
inner: HtmlSerializer<W>,
|
||||
at_beginning: bool,
|
||||
}
|
||||
|
||||
impl<W: Write> Serializer for PrettyPrint<W> {
|
||||
fn start_elem<'a, AttrIter>(&mut self, name: QualName, attrs: AttrIter) -> io::Result<()>
|
||||
where
|
||||
AttrIter: Iterator<Item = AttrRef<'a>>,
|
||||
{
|
||||
// Make attribute order deterministic.
|
||||
let mut attrs: Vec<_> = attrs.collect();
|
||||
attrs.sort();
|
||||
|
||||
let inline = is_inline(&name.local);
|
||||
if (!inline || self.previous_was_block) && !self.at_beginning {
|
||||
self.inner.writer.write_all(b"\n")?;
|
||||
self.inner.writer.write_all(&vec![b' '; self.indent])?;
|
||||
}
|
||||
|
||||
self.indent += 2;
|
||||
self.inner.start_elem(name, attrs.into_iter())?;
|
||||
|
||||
if self.at_beginning {
|
||||
self.at_beginning = false;
|
||||
self.previous_was_block = !inline;
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn end_elem(&mut self, name: QualName) -> io::Result<()> {
|
||||
self.indent -= 2;
|
||||
|
||||
if is_inline(&name.local) {
|
||||
self.previous_was_block = false;
|
||||
} else {
|
||||
self.inner.writer.write_all(b"\n")?;
|
||||
self.inner.writer.write_all(&vec![b' '; self.indent])?;
|
||||
self.previous_was_block = true;
|
||||
}
|
||||
|
||||
self.inner.end_elem(name)
|
||||
}
|
||||
|
||||
fn write_text(&mut self, text: &str) -> io::Result<()> {
|
||||
if text.trim().is_empty() {
|
||||
Ok(())
|
||||
} else {
|
||||
if self.previous_was_block {
|
||||
self.inner.writer.write_all(b"\n")?;
|
||||
self.inner.writer.write_all(&vec![b' '; self.indent])?;
|
||||
}
|
||||
|
||||
self.previous_was_block = false;
|
||||
self.inner.write_text(text)
|
||||
}
|
||||
}
|
||||
|
||||
fn write_comment(&mut self, text: &str) -> io::Result<()> {
|
||||
self.inner.write_comment(text)
|
||||
}
|
||||
|
||||
fn write_doctype(&mut self, name: &str) -> io::Result<()> {
|
||||
self.inner.write_doctype(name)
|
||||
}
|
||||
|
||||
fn write_processing_instruction(&mut self, target: &str, data: &str) -> io::Result<()> {
|
||||
self.inner.write_processing_instruction(target, data)
|
||||
}
|
||||
}
|
||||
4
tests/data/LICENSE
Normal file
4
tests/data/LICENSE
Normal file
|
|
@ -0,0 +1,4 @@
|
|||
The text in the child directories is content from Wikipedia, The Free Encyclopedia, and available under the Creative Commons Attribution-ShareAlike 3.0 Unported License (CC BY-SA).
|
||||
|
||||
The full license text and more information is available at:
|
||||
https://en.wikipedia.org/wiki/Wikipedia:Copyrights
|
||||
158
tests/data/Q4185820-en/original.html
Normal file
158
tests/data/Q4185820-en/original.html
Normal file
File diff suppressed because one or more lines are too long
239
tests/data/Q4185820-en/output.html
Normal file
239
tests/data/Q4185820-en/output.html
Normal file
|
|
@ -0,0 +1,239 @@
|
|||
<!DOCTYPE html><html about="https://en.wikipedia.org/wiki/Special:Redirect/revision/1143258291" prefix="dc: http://purl.org/dc/terms/ mw: http://mediawiki.org/rdf/">
|
||||
<head prefix="mwr: https://en.wikipedia.org/wiki/Special:Redirect/">
|
||||
<meta charset="utf-8">
|
||||
|
||||
<title>
|
||||
Thoor Ballylee
|
||||
</title>
|
||||
<meta content="en" http-equiv="content-language">
|
||||
|
||||
<meta content="Accept" http-equiv="vary">
|
||||
|
||||
</head>
|
||||
<body class="mw-content-ltr sitedir-ltr ltr mw-body-content parsoid-body mediawiki mw-parser-output" dir="ltr" id="mwAA" lang="en">
|
||||
<section data-mw-section-id="0" id="mwAQ">
|
||||
<p id="mwAg">
|
||||
<span about="#mwt1" data-mw="{"parts":[{"template":{"target":{"wt":"Coord","href":"./Template:Coord"},"params":{"1":{"wt":"53"},"2":{"wt":"06"},"3":{"wt":"11.4"},"4":{"wt":"N"},"5":{"wt":"08"},"6":{"wt":"46"},"7":{"wt":"29.2"},"8":{"wt":"W"},"display":{"wt":"title"}},"i":0}}]}" id="mwAw" style="font-size: small;" typeof="mw:Transclusion">
|
||||
<span id="coordinates">
|
||||
Coordinates:
|
||||
<style about="#mwt3" data-mw="{"name":"templatestyles","attrs":{"src":"Module:Coordinates/styles.css"},"body":{"extsrc":""}}" data-mw-deduplicate="TemplateStyles:r1073938472" typeof="mw:Extension/templatestyles">.mw-parser-output .geo-default,.mw-parser-output .geo-dms,.mw-parser-output .geo-dec{display:inline}.mw-parser-output .geo-nondefault,.mw-parser-output .geo-multi-punct{display:none}.mw-parser-output .longitude,.mw-parser-output .latitude{white-space:nowrap}
|
||||
</style>
|
||||
<span class="plainlinks nourlexpansion">
|
||||
<span class="geo-default">
|
||||
<span class="geo-dms" title="Maps, aerial photos, and other data for this location">
|
||||
<span class="latitude">
|
||||
53°06′11.4″N</span><span class="longitude">08°46′29.2″W</span></span></span><span class="geo-multi-punct"><span typeof="mw:Entity"></span> / <span typeof="mw:Entity"></span></span><span class="geo-nondefault"><span class="geo-dec" title="Maps, aerial photos, and other data for this location">53.103167°N 8.774778°W</span><span style="display:none"><span typeof="mw:Entity"></span> / <span class="geo">53.103167; -8.774778</span></span></span></span></span></span>
|
||||
</p>
|
||||
<div about="#mwt8" class="shortdescription nomobile noexcerpt noprint searchaux" data-mw="{"parts":[{"template":{"target":{"wt":"Infobox building\n","href":"./Template:Infobox_building"},"params":{"name":{"wt":"Thoor Ballylee"},"image":{"wt":"File:Thoor Ballylee002(js).jpg"},"map_type":{"wt":"Ireland"},"coordinates":{"wt":"{{coord|53.103|-8.775|display=inline}}"},"location":{"wt":"[[County Galway]], [[Ireland]]"},"owner":{"wt":"[[Earl of Clanricarde|Earls of Clanrickarde]], [[House of Burke|The Septs de Burgo]], [[William Butler Yeats]]"},"construction_start_date":{"wt":"15th (or 16th) century"},"completion_date":{"wt":"15th (or 16th) century"},"style":{"wt":"Anglo-Norman tower house"},"architect":{"wt":"[[House of Burke|The Septs de Burgo]]"},"other_designers":{"wt":"[[William Butler Yeats]], William A. Scott"},"civil_engineer":{"wt":""}},"i":0}}]}" id="mwCQ" style="display:none" typeof="mw:Transclusion">
|
||||
Building in County Galway, Ireland
|
||||
</div>
|
||||
<style about="#mwt8" data-mw="{"name":"templatestyles","attrs":{"src":"Module:Infobox/styles.css"},"body":{"extsrc":""}}" data-mw-deduplicate="TemplateStyles:r1066479718" typeof="mw:Extension/templatestyles">
|
||||
.mw-parser-output .infobox-subbox{padding:0;border:none;margin:-3px;width:auto;min-width:100%;font-size:100%;clear:none;float:none;background-color:transparent}.mw-parser-output .infobox-3cols-child{margin:auto}.mw-parser-output .infobox .navbar{font-size:100%}body.skin-minerva .mw-parser-output .infobox-header,body.skin-minerva .mw-parser-output .infobox-subheader,body.skin-minerva .mw-parser-output .infobox-above,body.skin-minerva .mw-parser-output .infobox-title,body.skin-minerva .mw-parser-output .infobox-image,body.skin-minerva .mw-parser-output .infobox-full-data,body.skin-minerva .mw-parser-output .infobox-below{text-align:center}
|
||||
</style>
|
||||
<table about="#mwt8" class="infobox vcard" id="mwCg">
|
||||
<tbody>
|
||||
<tr>
|
||||
<th class="infobox-above fn org" colspan="2">
|
||||
Thoor Ballylee
|
||||
</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td class="infobox-image" colspan="2" style="text-align: center">
|
||||
<style about="#mwt13" data-mw="{"name":"templatestyles","attrs":{"src":"Module:Location map/styles.css"},"body":{"extsrc":""}}" data-mw-deduplicate="TemplateStyles:r997900035" typeof="mw:Extension/templatestyles">
|
||||
.mw-parser-output .locmap .od{position:absolute}.mw-parser-output .locmap .id{position:absolute;line-height:0}.mw-parser-output .locmap .l0{font-size:0;position:absolute}.mw-parser-output .locmap .pv{line-height:110%;position:absolute;text-align:center}.mw-parser-output .locmap .pl{line-height:110%;position:absolute;top:-0.75em;text-align:right}.mw-parser-output .locmap .pr{line-height:110%;position:absolute;top:-0.75em;text-align:left}.mw-parser-output .locmap .pv>div{display:inline;padding:1px}.mw-parser-output .locmap .pl>div{display:inline;padding:1px;float:right}.mw-parser-output .locmap .pr>div{display:inline;padding:1px;float:left}
|
||||
</style>
|
||||
<div class="center">
|
||||
<div class="locmap" style="width:240px;float:none;clear:both;margin-left:auto;margin-right:auto">
|
||||
<div style="width:240px;padding:0">
|
||||
<div style="padding-top:0.2em">
|
||||
Location within Ireland
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-header" colspan="2" style="background-color:#ededed">
|
||||
General information
|
||||
</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-label" scope="row">
|
||||
Architectural style
|
||||
</th>
|
||||
<td class="infobox-data category">
|
||||
Anglo-Norman tower house
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-label" scope="row">
|
||||
Location
|
||||
</th>
|
||||
<td class="infobox-data label">
|
||||
County Galway, Ireland
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-label" scope="row">
|
||||
Coordinates
|
||||
</th>
|
||||
<td class="infobox-data">
|
||||
<span class="plainlinks nourlexpansion">
|
||||
<span class="geo-nondefault">
|
||||
<span class="geo-dms" title="Maps, aerial photos, and other data for this location">
|
||||
<span class="latitude">
|
||||
53°06′11″N</span><span class="longitude">8°46′30″W</span></span></span><span class="geo-multi-punct"><span typeof="mw:Entity"></span> / <span typeof="mw:Entity"></span></span><span class="geo-default"><span class="geo-dec" title="Maps, aerial photos, and other data for this location">53.103°N 8.775°W</span><span style="display:none"><span typeof="mw:Entity"></span> / <span class="geo">53.103; -8.775</span></span></span></span>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-label" scope="row">
|
||||
Construction started
|
||||
</th>
|
||||
<td class="infobox-data">
|
||||
15th (or 16th) century
|
||||
</td>
|
||||
</tr>
|
||||
<tr class="note">
|
||||
<th class="infobox-label" scope="row">
|
||||
Completed
|
||||
</th>
|
||||
<td class="infobox-data">
|
||||
15th (or 16th) century
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-label" scope="row">
|
||||
Owner
|
||||
</th>
|
||||
<td class="infobox-data">
|
||||
Earls of Clanrickarde, The Septs de Burgo, William Butler Yeats
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-header" colspan="2" style="background-color:#ededed">
|
||||
Design and construction
|
||||
</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-label" scope="row">
|
||||
Architect(s)
|
||||
</th>
|
||||
<td class="infobox-data">
|
||||
The Septs de Burgo
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-label" scope="row">
|
||||
Other designers
|
||||
</th>
|
||||
<td class="infobox-data">
|
||||
William Butler Yeats, William A. Scott
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<p id="mwCw">
|
||||
<b id="mwDA">
|
||||
Thoor Ballylee Castle</b> (Irish<i id="mwDg">Túr Bhaile Uí Laí</i>) is a fortified, 15th-century Anglo-Normantower house built by the septsde Burgo, or Burke, near the town of Gort in County Galway, Ireland. It is also known as <i id="mwFg">Yeats' Tower</i> because it was once owned and inhabited by the poet William Butler Yeats.
|
||||
</p>
|
||||
<p id="mwGA">
|
||||
It has been described as ‘the most important public building in Ireland’ by late Nobel laureate Seamus Heaney.<sup about="#mwt19" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-1"}}" id="cite_ref-1" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwGw">[1]</span></sup>
|
||||
</p>
|
||||
</section>
|
||||
<section data-mw-section-id="1" id="mwHA">
|
||||
<h2 id="History">
|
||||
History
|
||||
</h2>
|
||||
<p id="mwHQ">
|
||||
The castle was built in the 15th (or possibly 16th) century and originally formed part of the huge estates of the Earls of Clanricarde, from the de Burgo or Burke family.
|
||||
</p>
|
||||
<p id="mwIA">
|
||||
The nearby four-arched bridge dates to around 1825.<sup about="#mwt25" class="mw-ref reference" data-mw="{"name":"ref","attrs":{"name":"Invent"},"body":{"id":"mw-reference-text-cite_note-Invent-2"}}" id="cite_ref-Invent_2-0" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwIg">[2]</span></sup> In 1837, the Carrig family was recorded as living in the castle. At the time of Griffith's Valuation (1857), Patrick Carrick was leasing a herd's house, castle and land at Ballylee, barony of Kiltartan, from William Henry Gregory. At the time, the property was valued at £5.<sup about="#mwt29" class="mw-ref reference" data-mw="{"name":"ref","attrs":{"name":"Estate1"},"body":{"id":"mw-reference-text-cite_note-Estate1-3"}}" id="cite_ref-Estate1_3-0" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwJg">[3]</span></sup>
|
||||
</p>
|
||||
<p id="mwJw">
|
||||
In the early 1900s, the castle/tower was still owned by the Gregory family and became part of nearby Coole Estate, home of Lady Augusta Gregory, Yeats’ lifelong friend.<sup about="#mwt35" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-4"}}" id="cite_ref-4" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwKw">[4]</span></sup> On the estate, Coole House, where Lady Gregory lived, was the centre for meetings for the Irish literary group, a group composed of a great number of preeminent figures of the day. Near this tower, in Coole Park, began the Irish Literary Revival.<sup about="#mwt39" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-5"}}" id="cite_ref-5" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwLg">[5]</span></sup>
|
||||
</p>
|
||||
<p id="mwLw">
|
||||
Thoor Ballylee is also known today as <b id="mwMA">Yeats’ Tower</b>, because in 1916 (or 1917) Yeats purchased the property for the nominal sum of £35 because he was so enchanted with it and especially as it was located in a rural area.<sup about="#mwt49" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-6"}}" id="cite_ref-6" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwMg">[6]</span></sup> From 1921 to 1929,<sup about="#mwt53" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-7"}}" id="cite_ref-7" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwNA">[7]</span></sup><sup about="#mwt57" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-8"}}" id="cite_ref-8" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwNg">[8]</span></sup> Yeats and his family lived there as it was his monument and symbol: In both aspects, it satisfied his desire for a rooted place in the countryside.<sup about="#mwt61" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-9"}}" id="cite_ref-9" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwOA">[9]</span></sup> The tower retained its original windows in the upper part. Yeats and his architect, Professor William A. Scott, restored the tower for the next two years and installed larger windows in the lower floors.<sup about="#mwt65" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-10"}}" id="cite_ref-10" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwOg">[10]</span></sup><sup about="#mwt69" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-11"}}" id="cite_ref-11" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwPA">[11]</span></sup>
|
||||
</p>
|
||||
<p id="mwPQ">
|
||||
As he had an affinity for the Irish language, Yeats dropped the term "castle" in naming the property and replaced it with "<i id="mwPg">Thoor</i>" (<i id="mwPw">Túr</i>), the Irish word for "tower"; thus, the place has been known as Thoor Ballylee. For twelve years, Thoor Ballylee was Yeats’ summer home as it was his country retreat. In a letter to a friend, he wrote, "Everything is so beautiful that to go elsewhere is to leave beauty behind." Consequently, it is no wonder that Yeats was inspired and compelled to create literary works at Ballylee such as poems like <i id="mwQA">The Tower</i> and <i id="mwQQ">Coole Park and Ballylee</i>.<sup about="#mwt74" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-12"}}" id="cite_ref-12" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwQw">[12]</span></sup>
|
||||
</p>
|
||||
<p id="mwRA">
|
||||
In 1929, Ballylee was abandoned as the Yeats family moved out and it fell to disuse and ruin.<sup about="#mwt79" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-13"}}" id="cite_ref-13" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwRg">[13]</span></sup>
|
||||
</p>
|
||||
<p id="mwRw">
|
||||
In 1951, a scene of John Ford's The Quiet Man in which John Wayne and Maureen O'Hara cross a river was shot next to Thoor Ballylee.
|
||||
</p>
|
||||
<p id="mwTA">
|
||||
Mary Hanley (1914-1979) was the founder of the Kiltartan Society. A native of Carron, County Clare, Hanley founded the society in 1961 to foster interest in the literary history of the district, especially that of Lady Gregory, Edward Martyn and W.B. Yeats. She was responsible for the restoration of Thoor Ballylee (with the aid of Bord Fáilte and the Yeats family). At the time, the Office of Public Works was owner of the property. Hanley persuaded the poet Padraic Colum to open the castle on Sunday 20 June 1965, the centenary of Yeats’s birth, as <i id="mwVA">Yeats Tower</i> to appear as it was when he lived there and refitted as a Yeats museum containing a collection of first editions and items of furniture.<sup about="#mwt84" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-14"}}" id="cite_ref-14" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwVg">[14]</span></sup> The adjoining miller's cottage became a tea room and shop. This was later expanded by a newly constructed building in the back.
|
||||
</p>
|
||||
</section>
|
||||
<section data-mw-section-id="2" id="mwVw">
|
||||
<h2 id="Today">
|
||||
Today
|
||||
</h2>
|
||||
<p id="mwWA">
|
||||
Due to its proximity to the Streamstown River, Thoor Ballylee is subject to sporadic flooding. This occurred notably in 1995 and in 2009/2010. In 2009, Thoor Ballylee was extensively damaged by flooding.<sup about="#mwt91" class="mw-ref reference" data-mw="{"name":"ref","attrs":{"name":"Website"},"body":{"id":"mw-reference-text-cite_note-Website-15"}}" id="cite_ref-Website_15-0" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwWg">[15]</span></sup><sup about="#mwt96" class="mw-ref reference" data-mw="{"name":"ref","attrs":{"name":"CC1"},"body":{"id":"mw-reference-text-cite_note-CC1-16"}}" id="cite_ref-CC1_16-0" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwXA">[16]</span></sup> For a while it appeared that due to the financial problems of the Irish government, no money would be available to repair it.<sup about="#mwt100" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-17"}}" id="cite_ref-17" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwXg">[17]</span></sup>
|
||||
</p>
|
||||
<p id="mwXw">
|
||||
Thus only in February 2012 did work by Fáilte Ireland on restoring the tower begin, although no opening date was envisaged at the time.<sup about="#mwt107" class="mw-ref reference" data-mw="{"name":"ref","attrs":{"name":"CC"},"body":{"id":"mw-reference-text-cite_note-CC-18"}}" id="cite_ref-CC_18-0" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwYg">[18]</span></sup> One of the forces behind the decision to repair the tower had been East Galway senator Lorraine Higgins, who argued that a reopened Yeats' Tower would be a boon to local tourism.<sup about="#mwt111" class="mw-ref reference" data-mw="{"name":"ref","attrs":{"name":"Higgins"},"body":{"id":"mw-reference-text-cite_note-Higgins-19"}}" id="cite_ref-Higgins_19-0" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwZQ">[19]</span></sup>
|
||||
</p>
|
||||
<p id="mwZg">
|
||||
By February 2013 the tower had still not reopened. However, a private group — in cooperation with Fáilte Ireland — had engaged the services of Galway Rural Development, a make-work-scheme, for the maintenance work.<sup about="#mwt116" class="mw-ref reference" data-mw="{"name":"ref","attrs":{"name":"GA"},"body":{"id":"mw-reference-text-cite_note-GA-20"}}" id="cite_ref-GA_20-0" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwaA">[20]</span></sup>
|
||||
</p>
|
||||
<p id="mwaQ">
|
||||
In 2014, a local community group the "Yeats Thoor Ballylee Society" leased Thoor Ballylee from Fáilte Ireland to develop it into a culture and education centre, in time for the Yeats 150th Anniversary in June 2015. The Society is cooperating with the National Yeats Steering Committee and the Yeats Society to ensure that Thoor Ballylee is an integrated part of the Yeats 2015 celebrations.<sup about="#mwt121" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-21"}}" id="cite_ref-21" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwaw">[21]</span></sup>
|
||||
</p>
|
||||
<p id="mwbA">
|
||||
In early December 2015, Storm Desmond devastated parts of Ireland with flooding rain and damaging winds. Thoor Ballylee, and the adjacent cottage, were both damaged by several feet of flood water.
|
||||
</p>
|
||||
</section>
|
||||
<section data-mw-section-id="3" id="mwbg">
|
||||
<h2 id="Architecture">
|
||||
Architecture
|
||||
</h2>
|
||||
<figure class="mw-default-size" id="mwbw" typeof="mw:File/Thumb">
|
||||
<figcaption id="mwcg">
|
||||
Inscription on tower composed by WB Yeats.
|
||||
</figcaption>
|
||||
</figure>
|
||||
<p id="mwcw">
|
||||
With four floors, the tower consists of one room on each floor that is connected by a spiral stone stairway built into the seven-foot thickness of the massive outer wall. Each floor has a window that overlooks the Streamstown River that flows alongside the tower. There is a small thatch cottage attached.
|
||||
</p>
|
||||
<p id="mwdA">
|
||||
Yeats described the ground-floor chamber as "the pleasantest room I have yet seen, a great wide window opening over the river and a round arched door leading to the thatched hall". He also admired the mural stair, symbolically declaring "This winding, gyring, spiring treadmill of a stair is my ancestral stair; That Goldsmith and the Dean, Berkeley and Burke have traveled there."<sup about="#mwt127" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-22"}}" id="cite_ref-22" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwdg">[22]</span></sup><sup about="#mwt131" class="mw-ref reference" data-mw="{"name":"ref","attrs":{},"body":{"id":"mw-reference-text-cite_note-23"}}" id="cite_ref-23" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mweA">[23]</span></sup>
|
||||
</p>
|
||||
<p id="mweQ">
|
||||
There is a tablet on the wall that commemorates Yeats' sojourn:<sup about="#mwt136" class="mw-ref reference" data-mw="{"name":"ref","attrs":{"name":"Invent2"},"body":{"id":"mw-reference-text-cite_note-Invent2-24"}}" id="cite_ref-Invent2_24-0" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwew">[24]</span></sup>
|
||||
</p>
|
||||
<blockquote id="mwfA">
|
||||
<p id="mwfQ">
|
||||
<i id="mwfg">
|
||||
I, the poet William Yeats,</i>
|
||||
</p>
|
||||
<p id="mwfw">
|
||||
<i id="mwgA">
|
||||
With old mill boards and sea-green slates,</i>
|
||||
</p>
|
||||
<p id="mwgQ">
|
||||
<i id="mwgg">
|
||||
And smithy work from the Gort forge,</i>
|
||||
</p>
|
||||
<p id="mwgw">
|
||||
<i id="mwhA">
|
||||
Restored this tower for my wife George.</i>
|
||||
</p>
|
||||
<p id="mwhQ">
|
||||
<i id="mwhg">
|
||||
And may these characters remain</i>
|
||||
</p>
|
||||
<p id="mwhw">
|
||||
<i id="mwiA">
|
||||
When all is ruin once again.</i>
|
||||
</p>
|
||||
</blockquote>
|
||||
</section>
|
||||
</body>
|
||||
</html>
|
||||
182
tests/data/Q748282-en/original.html
Normal file
182
tests/data/Q748282-en/original.html
Normal file
File diff suppressed because one or more lines are too long
278
tests/data/Q748282-en/output.html
Normal file
278
tests/data/Q748282-en/output.html
Normal file
|
|
@ -0,0 +1,278 @@
|
|||
<!DOCTYPE html><html about="https://en.wikipedia.org/wiki/Special:Redirect/revision/1147024636" prefix="dc: http://purl.org/dc/terms/ mw: http://mediawiki.org/rdf/">
|
||||
<head prefix="mwr: https://en.wikipedia.org/wiki/Special:Redirect/">
|
||||
<meta charset="utf-8">
|
||||
|
||||
<title>
|
||||
Crimean Mountains
|
||||
</title>
|
||||
<meta content="en" http-equiv="content-language">
|
||||
|
||||
<meta content="Accept" http-equiv="vary">
|
||||
|
||||
</head>
|
||||
<body class="mw-content-ltr sitedir-ltr ltr mw-body-content parsoid-body mediawiki mw-parser-output" dir="ltr" id="mwAA" lang="en">
|
||||
<section data-mw-section-id="0" id="mwAQ">
|
||||
<div about="#mwt1" class="shortdescription nomobile noexcerpt noprint searchaux" data-mw="{"parts":[{"template":{"target":{"wt":"Short description","href":"./Template:Short_description"},"params":{"1":{"wt":"Mountain range along the southeastern coast of Crimea"}},"i":0}}]}" id="mwAg" style="display:none" typeof="mw:Transclusion">
|
||||
Mountain range along the southeastern coast of Crimea
|
||||
</div>
|
||||
<style about="#mwt2" data-mw="{"parts":[{"template":{"target":{"wt":"Infobox mountain\n","href":"./Template:Infobox_mountain"},"params":{"name":{"wt":"Crimean Mountains"},"other_name":{"wt":""},"photo":{"wt":"Сутінки на схилах Демерджі.jpg"},"native_name":{"wt":"{{native name list |tag1=crh|name1=Qırım dağları|tag2=uk|name2=Кримські гори|tag3=ru|name3=Крымские горы}}"},"photo_size":{"wt":"250"},"photo_alt":{"wt":""},"photo_caption":{"wt":"Twilight on [[Demirci yayla]]"},"map":{"wt":""},"map_image":{"wt":"Южный Крым.png"},"map_alt":{"wt":""},"map_caption":{"wt":""},"map_relief":{"wt":""},"map_size":{"wt":""},"highest":{"wt":"[[Roman-Kosh]]"},"location":{"wt":"Southern [[Crimea]]"},"label":{"wt":""},"label_position":{"wt":""},"elevation":{"wt":""},"elevation_m":{"wt":"1545"},"elevation_ft":{"wt":""},"elevation_ref":{"wt":""},"prominence":{"wt":""},"prominence_m":{"wt":""},"prominence_ft":{"wt":""},"prominence_ref":{"wt":""},"isolation":{"wt":""},"isolation_km":{"wt":""},"isolation_mi":{"wt":""},"isolation_ref":{"wt":""},"parent_peak":{"wt":""},"listing":{"wt":""},"translation":{"wt":""},"language":{"wt":""},"pronunciation":{"wt":""},"range":{"wt":""},"coordinates":{"wt":"{{coord|44|36|47|N|34|14|36|E|type:mountain_scale:100000|format=dms|display=inline}}"},"range_coordinates":{"wt":"{{coord|44|45|N|34|30|E|region:UA_type:mountain|display=title,inline}}"},"coordinates_ref":{"wt":""},"topo":{"wt":""},"type":{"wt":""},"age":{"wt":"[[Cretaceous]]"},"volcanic_arc":{"wt":""},"volcanic_belt":{"wt":""},"volcanic_field":{"wt":""},"volcanic_arc/belt":{"wt":""},"last_eruption":{"wt":""},"first_ascent":{"wt":""},"easiest_route":{"wt":""},"normal_route":{"wt":""},"access":{"wt":""},"child":{"wt":""},"embedded":{"wt":""}},"i":0}}]}" data-mw-deduplicate="TemplateStyles:r1066479718" id="mwBA" typeof="mw:Extension/templatestyles mw:Transclusion">
|
||||
.mw-parser-output .infobox-subbox{padding:0;border:none;margin:-3px;width:auto;min-width:100%;font-size:100%;clear:none;float:none;background-color:transparent}.mw-parser-output .infobox-3cols-child{margin:auto}.mw-parser-output .infobox .navbar{font-size:100%}body.skin-minerva .mw-parser-output .infobox-header,body.skin-minerva .mw-parser-output .infobox-subheader,body.skin-minerva .mw-parser-output .infobox-above,body.skin-minerva .mw-parser-output .infobox-title,body.skin-minerva .mw-parser-output .infobox-image,body.skin-minerva .mw-parser-output .infobox-full-data,body.skin-minerva .mw-parser-output .infobox-below{text-align:center}
|
||||
</style>
|
||||
<table about="#mwt2" class="infobox vcard" id="mwBQ" style="width:24.5em; line-height:1.5em;">
|
||||
<tbody>
|
||||
<tr>
|
||||
<th class="infobox-above fn org" colspan="2" style="background-color: #E7DCC3;">
|
||||
Crimean Mountains
|
||||
</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td class="infobox-image" colspan="2" style="padding: 0.3em 0.2em 0.2em 0.2em;">
|
||||
<div class="infobox-caption" style="padding: 0.2em 0em;">
|
||||
Twilight on Demirci yayla
|
||||
</div>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-header" colspan="2" style="background-color: #E7DCC3;">
|
||||
Highestpoint
|
||||
</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-label" scope="row">
|
||||
Peak
|
||||
</th>
|
||||
<td class="infobox-data">
|
||||
Roman-Kosh
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-label" scope="row">
|
||||
Elevation
|
||||
</th>
|
||||
<td class="infobox-data">
|
||||
1,545m (5,069ft)
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-label" scope="row">
|
||||
Coordinates
|
||||
</th>
|
||||
<td class="infobox-data">
|
||||
<style about="#mwt9" data-mw="{"name":"templatestyles","attrs":{"src":"Module:Coordinates/styles.css"},"body":{"extsrc":""}}" data-mw-deduplicate="TemplateStyles:r1073938472" typeof="mw:Extension/templatestyles">
|
||||
.mw-parser-output .geo-default,.mw-parser-output .geo-dms,.mw-parser-output .geo-dec{display:inline}.mw-parser-output .geo-nondefault,.mw-parser-output .geo-multi-punct{display:none}.mw-parser-output .longitude,.mw-parser-output .latitude{white-space:nowrap}
|
||||
</style>
|
||||
<span class="plainlinks nourlexpansion">
|
||||
<span class="geo-default">
|
||||
<span class="geo-dms" title="Maps, aerial photos, and other data for this location">
|
||||
<span class="latitude">
|
||||
44°36′47″N</span><span class="longitude">34°14′36″E</span></span></span><span class="geo-multi-punct"><span typeof="mw:Entity"></span> / <span typeof="mw:Entity"></span></span><span class="geo-nondefault"><span class="geo-dec" title="Maps, aerial photos, and other data for this location">44.61306°N 34.24333°E</span><span style="display:none"><span typeof="mw:Entity"></span> / <span class="geo">44.61306; 34.24333</span></span></span></span>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-header" colspan="2" style="background-color: #E7DCC3;">
|
||||
Naming
|
||||
</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-label" scope="row">
|
||||
Native name
|
||||
</th>
|
||||
<td class="infobox-data nickname">
|
||||
<style about="#mwt10" data-mw="{"name":"templatestyles","attrs":{"src":"Plainlist/styles.css"},"body":{"extsrc":""}}" data-mw-deduplicate="TemplateStyles:r1126788409" typeof="mw:Extension/templatestyles">
|
||||
.mw-parser-output .plainlist ol,.mw-parser-output .plainlist ul{line-height:inherit;list-style:none;margin:0;padding:0}.mw-parser-output .plainlist ol li,.mw-parser-output .plainlist ul li{margin-bottom:0}
|
||||
</style>
|
||||
<div class="plainlist">
|
||||
<ul>
|
||||
<li>
|
||||
<span title="Crimean Tatar-language text">
|
||||
<i lang="crh">
|
||||
Qırım dağları</i></span><span class="languageicon" style="font-size:100%; font-weight:normal">(Crimean Tatar)</span>
|
||||
</li>
|
||||
<li>
|
||||
<span title="Ukrainian-language text">
|
||||
<span lang="uk">
|
||||
Кримські гори</span></span><span class="languageicon" style="font-size:100%; font-weight:normal">(Ukrainian)</span>
|
||||
</li>
|
||||
<li>
|
||||
<span title="Russian-language text">
|
||||
<span lang="ru">
|
||||
Крымские горы</span></span><span class="languageicon" style="font-size:100%; font-weight:normal">(Russian)</span>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-header" colspan="2" style="background-color: #E7DCC3;">
|
||||
Geography
|
||||
</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-label" scope="row">
|
||||
Location
|
||||
</th>
|
||||
<td class="infobox-data label">
|
||||
Southern Crimea
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-label" scope="row">
|
||||
Range coordinates
|
||||
</th>
|
||||
<td class="infobox-data">
|
||||
<span class="plainlinks nourlexpansion">
|
||||
<span class="geo-default">
|
||||
<span class="geo-dms" title="Maps, aerial photos, and other data for this location">
|
||||
<span class="latitude">
|
||||
44°45′N</span><span class="longitude">34°30′E</span></span></span><span class="geo-multi-punct"><span typeof="mw:Entity"></span> / <span typeof="mw:Entity"></span></span><span class="geo-nondefault"><span class="geo-dec" title="Maps, aerial photos, and other data for this location">44.750°N 34.500°E</span><span style="display:none"><span typeof="mw:Entity"></span> / <span class="geo">44.750; 34.500</span></span></span></span><span style="font-size: small;"><span id="coordinates">Coordinates: <span class="plainlinks nourlexpansion"><span class="geo-default"><span class="geo-dms" title="Maps, aerial photos, and other data for this location"><span class="latitude">44°45′N</span><span class="longitude">34°30′E</span></span></span><span class="geo-multi-punct"><span typeof="mw:Entity"></span> / <span typeof="mw:Entity"></span></span><span class="geo-nondefault"><span class="geo-dec" title="Maps, aerial photos, and other data for this location">44.750°N 34.500°E</span><span style="display:none"><span typeof="mw:Entity"></span> / <span class="geo">44.750; 34.500</span></span></span></span></span></span>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-header" colspan="2" style="background-color: #E7DCC3;">
|
||||
Geology
|
||||
</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<th class="infobox-label" scope="row">
|
||||
Age of rock
|
||||
</th>
|
||||
<td class="infobox-data">
|
||||
Cretaceous
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<p id="mwBg">
|
||||
The <b id="mwBw">Crimean Mountains</b> (Crimean Tatar<span about="#mwt13">: </span><span about="#mwt13" lang="crh">Qırım dağları</span>; Ukrainian<span about="#mwt14">: </span><span about="#mwt14" lang="uk">Кримські гори</span>; Russian<span about="#mwt15">: </span><span about="#mwt15" lang="ru">Крымские горы</span>; Turkish<span about="#mwt16">: </span><i about="#mwt16" lang="tr">Yayla Dağları</i>) or <b id="mwEA">Yayla Mountains</b> are a range of mountains running parallel to the south-eastern coast of Crimea, between about <span about="#mwt17" data-mw="{"parts":[{"template":{"target":{"wt":"convert","href":"./Template:Convert"},"params":{"1":{"wt":"8–13"},"2":{"wt":"km"},"3":{"wt":"mi"},"frac":{"wt":"2"},"abbr":{"wt":"off"},"sp":{"wt":"us"}},"i":0}}]}" id="mwFA" typeof="mw:Transclusion">8–13 kilometers (5–8 miles)</span> from the sea. Toward the west, the mountains drop steeply to the Black Sea, and to the east, they change slowly into a steppe landscape.
|
||||
</p>
|
||||
<p id="mwFw">
|
||||
The Crimean Mountains consist of three subranges. The highest is the Main Range, which is subdivided into several yaylas or mountain plateaus (<i id="mwGQ">yayla</i> or <i id="mwGg">yaylak</i> is Turkic for "alpine meadow"). They are:
|
||||
</p>
|
||||
<ul id="mwHQ">
|
||||
<li id="mwHg">
|
||||
Baydar yayla
|
||||
</li>
|
||||
<li id="mwHw">
|
||||
Ai-Petri yayla
|
||||
</li>
|
||||
<li id="mwIQ">
|
||||
Yalta yayla
|
||||
</li>
|
||||
<li id="mwIw">
|
||||
Nikita yayla
|
||||
</li>
|
||||
<li id="mwJQ">
|
||||
Hurzuf yayla
|
||||
</li>
|
||||
<li id="mwJw">
|
||||
Babugan yayla
|
||||
</li>
|
||||
<li id="mwKA">
|
||||
Chatyr-Dag yayla
|
||||
</li>
|
||||
<li id="mwKg">
|
||||
Dologorukovskaya (Subatkan) yayla
|
||||
</li>
|
||||
<li id="mwKw">
|
||||
Demirci yayla
|
||||
</li>
|
||||
<li id="mwLQ">
|
||||
Qarabiy yayla
|
||||
</li>
|
||||
</ul>
|
||||
</section>
|
||||
<section data-mw-section-id="1" id="mwLw">
|
||||
<h2 id="Highest_peaks">
|
||||
Highest peaks
|
||||
</h2>
|
||||
<p id="mwMA">
|
||||
The Crimea's highest peak is the Roman-Kosh (Ukrainian<span about="#mwt18">: </span><span about="#mwt18" lang="uk">Роман-Кош</span>; Russian<span about="#mwt19">: </span><span about="#mwt19" lang="ru">Роман-Кош</span>, Crimean Tatar<span about="#mwt20">: </span><span about="#mwt20" lang="crh">Roman Qoş</span>) on the Babugan Yayla at <span about="#mwt21" data-mw="{"parts":[{"template":{"target":{"wt":"convert","href":"./Template:Convert"},"params":{"1":{"wt":"1545"},"2":{"wt":"m"}},"i":0}}]}" id="mwOA" typeof="mw:Transclusion">1,545 metres (5,069</span><span about="#mwt21">ft)</span>. Other important peaks over 1,200 metres include:
|
||||
</p>
|
||||
<ul id="mwOQ">
|
||||
<li id="mwOg">
|
||||
Demir-Kapu (Ukrainian<span about="#mwt22">: </span><span about="#mwt22" lang="uk">Демір-Капу</span>, Russian<span about="#mwt23">: </span><span about="#mwt23" lang="ru">Демир-Капу</span>, Crimean Tatar<span about="#mwt24">: </span><span about="#mwt24" lang="crh">Demir Qapı</span>) 1,540 m in the Babugan Yayla;
|
||||
</li>
|
||||
<li id="mwQg">
|
||||
Zeytin-Kosh (Ukrainian<span about="#mwt25">: </span><span about="#mwt25" lang="uk">Зейтин-Кош</span>; Russian<span about="#mwt26">: </span><span about="#mwt26" lang="ru">Зейтин-Кош</span>, Crimean Tatar<span about="#mwt27">: </span><span about="#mwt27" lang="crh">Zeytün Qoş</span>) 1,537 m in the Babugan Yayla;
|
||||
</li>
|
||||
<li id="mwSQ">
|
||||
Kemal-Egerek (Ukrainian<span about="#mwt28">: </span><span about="#mwt28" lang="uk">Кемаль-Егерек</span>, Russian<span about="#mwt29">: </span><span about="#mwt29" lang="ru">Кемаль-Эгерек</span>, Crimean Tatar<span about="#mwt30">: </span><span about="#mwt30" lang="crh">Kemal Egerek</span>) 1,529 m in the Babugan Yayla;
|
||||
</li>
|
||||
<li id="mwUA">
|
||||
Eklizi-Burun (Ukrainian<span about="#mwt31">: </span><span about="#mwt31" lang="uk">Еклізі-Бурун</span>, Russian<span about="#mwt32">: </span><span about="#mwt32" lang="ru">Эклизи-Бурун</span>, Crimean Tatar<span about="#mwt33">: </span><span about="#mwt33" lang="crh">Eklizi Burun</span>) 1,527 m in the Chatyrdag Yayla;
|
||||
</li>
|
||||
<li id="mwVw">
|
||||
Lapata (Ukrainian<span about="#mwt34">: </span><span about="#mwt34" lang="uk">Лапата</span>; Russian<span about="#mwt35">: </span><span about="#mwt35" lang="ru">Лапата</span>, Crimean Tatar<span about="#mwt36">: </span><span about="#mwt36" lang="crh">Lapata</span>) 1,406 m in the Yaltynska Yayla, Yalta Yaylası;
|
||||
</li>
|
||||
<li id="mwXg">
|
||||
Northern Demirji (Ukrainian<span about="#mwt37">: </span><span about="#mwt37" lang="uk">Північний Демірджі</span>, Russian<span about="#mwt38">: </span><span about="#mwt38" lang="ru">Северный Демирджи</span>, Crimean Tatar<span about="#mwt39">: </span><span about="#mwt39" lang="crh">Şimaliy Demirci</span>) 1,356 m in the Demirci Yayla;
|
||||
</li>
|
||||
<li id="mwZQ">
|
||||
Ai-Petri (Ukrainian<span about="#mwt40">: </span><span about="#mwt40" lang="uk">Ай-Петрі</span>, Russian<span about="#mwt41">: </span><span about="#mwt41" lang="ru">Ай-Петри</span>, Crimean Tatar<span about="#mwt42">: </span><span about="#mwt42" lang="crh">Ay Petri</span>) 1,234 m in the Ay Petri Yaylası.
|
||||
</li>
|
||||
</ul>
|
||||
</section>
|
||||
<section data-mw-section-id="2" id="mwbQ">
|
||||
<h2 id="Passes_and_rivers">
|
||||
Passes and rivers
|
||||
</h2>
|
||||
<p id="mwbg">
|
||||
The passes over the Crimean Mountains are: (from east to west)
|
||||
</p>
|
||||
<ul id="mwbw">
|
||||
<li id="mwcA">
|
||||
Angarskyi Pass (752m) near Perevalne, on a road from Alushta to Simferopol
|
||||
</li>
|
||||
<li id="mwdQ">
|
||||
Baydar Gate (503m) near Foros, connecting Baydar Valley and the sea coast
|
||||
</li>
|
||||
<li id="mweQ">
|
||||
Laspi Pass (350m) near Cape Aya, on a road from Yalta to Sevastopol.
|
||||
</li>
|
||||
</ul>
|
||||
<p id="mwfg">
|
||||
Rivers of the Crimean Mountains include the Alma River, Chernaya River, and Salhir River on the northern slope and Uchan-su River on the southern slope which forms the Uchan-su waterfall, and the highest waterfall in Crimea.
|
||||
</p>
|
||||
</section>
|
||||
<section data-mw-section-id="3" id="mwhA">
|
||||
<h2 id="History">
|
||||
History
|
||||
</h2>
|
||||
<p id="mwhQ">
|
||||
Archaeologists have found the earliest anatomically modern humans in Europe in the Crimean Mountains' Buran-Kaya caves. The fossils are 32,000 years old, with the artifacts linked to the Gravettian culture. The fossils have cut marks suggesting a post-mortem defleshing ritual.<sup about="#mwt48" class="mw-ref reference" data-mw="{"name":"ref","attrs":{"name":"orig"},"body":{"id":"mw-reference-text-cite_note-orig-1"}}" id="cite_ref-orig_1-0" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwig">[1]</span></sup><sup about="#mwt52" class="mw-ref reference" data-mw="{"name":"ref","attrs":{"name":"bbc"},"body":{"id":"mw-reference-text-cite_note-bbc-2"}}" id="cite_ref-bbc_2-0" rel="dc:references" typeof="mw:Extension/ref"><span class="mw-reflink-text" id="mwjA">[2]</span></sup>
|
||||
</p>
|
||||
</section>
|
||||
<section data-mw-section-id="4" id="mwjQ">
|
||||
<h2 id="Gallery">
|
||||
Gallery
|
||||
</h2>
|
||||
<ul about="#mwt54" class="gallery mw-gallery-traditional" data-mw="{"name":"gallery","attrs":{"perrow":"5"},"body":{"extsrc":"\nImage:Karabi_mountain_plateau.jpg|Qarabiy yayla\nImage:Karabi_mountain_plateau2.jpg|Qarabiy yayla\nImage:Karabi_mountain_plateau3.jpg|Qarabiy yayla\nImage:Chatyr_dag_plateau2.jpg|Mountain plateau of Chatyr-Dag mountain\nImage:Crimean mountains.jpg|The Crimean Mountains\n"}}" id="mwjg" style="max-width: 815px;" typeof="mw:Extension/gallery">
|
||||
<li class="gallerybox" id="mwjw" style="width: 155px;">
|
||||
<div class="gallerytext" id="mwlA">
|
||||
Qarabiy yayla
|
||||
</div>
|
||||
</li>
|
||||
<li class="gallerybox" id="mwlQ" style="width: 155px;">
|
||||
<div class="gallerytext" id="mwmg">
|
||||
Qarabiy yayla
|
||||
</div>
|
||||
</li>
|
||||
<li class="gallerybox" id="mwmw" style="width: 155px;">
|
||||
<div class="gallerytext" id="mwoA">
|
||||
Qarabiy yayla
|
||||
</div>
|
||||
</li>
|
||||
<li class="gallerybox" id="mwoQ" style="width: 155px;">
|
||||
<div class="gallerytext" id="mwpg">
|
||||
Mountain plateau of Chatyr-Dag mountain
|
||||
</div>
|
||||
</li>
|
||||
<li class="gallerybox" id="mwpw" style="width: 155px;">
|
||||
<div class="gallerytext" id="mwrA">
|
||||
The Crimean Mountains
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
</section>
|
||||
</body>
|
||||
</html>
|
||||
33
tests/html.rs
Normal file
33
tests/html.rs
Normal file
|
|
@ -0,0 +1,33 @@
|
|||
//! Tests to check for changes in HTML output.
|
||||
//!
|
||||
//! To update the expected output, run the test again with the env variable
|
||||
//! `UPDATE_EXPECT=1` set.
|
||||
//! See https://docs.rs/expect-test/ for more information.
|
||||
use om_wikiparser::html::{pretty_print, simplify_html};
|
||||
|
||||
use expect_test::{expect_file, ExpectFile};
|
||||
use scraper::Html;
|
||||
|
||||
fn check(input: &str, expect: ExpectFile) {
|
||||
let mut html = Html::parse_document(input);
|
||||
simplify_html(&mut html, "en");
|
||||
let processed = pretty_print(&html);
|
||||
|
||||
expect.assert_eq(&processed);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn simplify_crimean_mountains() {
|
||||
check(
|
||||
include_str!("./data/Q748282-en/original.html"),
|
||||
expect_file!["./data/Q748282-en/output.html"],
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn simplify_thoor_ballylee() {
|
||||
check(
|
||||
include_str!("./data/Q4185820-en/original.html"),
|
||||
expect_file!["./data/Q4185820-en/output.html"],
|
||||
);
|
||||
}
|
||||
Loading…
Add table
Reference in a new issue