Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix m-070 and add tests #732

Merged
merged 5 commits into from
Jul 25, 2024
Merged

Fix m-070 and add tests #732

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
21dd6d5
Add test demonstrating erroneous behavior of m-070
apasel422 Jul 13, 2024
ab2b45e
Fix m-070
apasel422 Jul 13, 2024
1f78ebb
Replace word boundaries with negative assertions
apasel422 Jul 13, 2024
9545297
Properly handle noterefs in m-070
apasel422 Jul 15, 2024
b089973
Vary m-070 searches based on whether <match> has children
apasel422 Jul 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 17 additions & 4 deletions se/se_epub_lint.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3515,7 +3515,15 @@ def lint(self, skip_lint_ignore: bool, allowed_messages: Optional[List[str]] = N
if filename.name == "glossary-search-key-map.xml":
ebook_flags["has_glossary_search_key_map"] = True
# Map the glossary to tuples of the values and whether they’re used (initially false)
glossary_usage = list(map(lambda node: (node.get_attr("value"), False), xml_dom.xpath(".//*[@value]")))
# If a <match> has no <value> children, its @value must appear in the text
# Otherwise, each of its <value> children's @value must appear
for match in xml_dom.xpath("/search-key-map/search-key-group/match[@value]"):
values = match.xpath("./value[@value]")
if not values:
glossary_usage.append((match.get_attr("value"), False))
else:
for value in values:
glossary_usage.append((value.get_attr("value"), False))

if filename.suffix == ".xhtml":
# Read file contents into a DOM for querying
Expand Down Expand Up @@ -3614,12 +3622,17 @@ def lint(self, skip_lint_ignore: bool, allowed_messages: Optional[List[str]] = N

# Check and log missing glossary keys
if ebook_flags["has_glossary_search_key_map"] and filename.name not in IGNORED_FILENAMES:
source_text = dom.xpath("/html/body")[0].inner_text()
# Remove all noterefs, as their anchor text will otherwise immediately follow a potential glossary term, defeating the below regex.
dom_copy = deepcopy(dom)
for node in dom_copy.xpath(".//a[contains(@epub:type, 'noteref')]"):
node.remove()

source_text = dom_copy.xpath("/html/body")[0].inner_text()
if dom.xpath("/html/body//section[contains(@epub:type, 'glossary')]"):
nodes = dom.xpath("/html/body//dd[contains(@epub:type, 'glossdef')]")
nodes = dom_copy.xpath("/html/body//dd[contains(@epub:type, 'glossdef')]")
source_text = " ".join([node.inner_text() for node in nodes])
for glossary_index, glossary_value in enumerate(glossary_usage):
if glossary_value[1] is False and regex.search(glossary_value[0], source_text, flags=regex.IGNORECASE):
if glossary_value[1] is False and regex.search(r"(?<!\w)\L<val>(?!\w)", source_text, flags=regex.IGNORECASE, val=[glossary_value[0]]):
glossary_usage[glossary_index] = (glossary_value[0], True)

# Test against word boundaries to not match `halftitlepage`
Expand Down
3 changes: 3 additions & 0 deletions tests/lint/metadata/m-070/golden/m-070-out.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
m-070 [Error] glossary-search-key-map.xml Glossary entry not found in the text.
foo
pariahsss
24 changes: 24 additions & 0 deletions tests/lint/metadata/m-070/in/src/epub/glossary-search-key-map.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
<?xml version="1.0" encoding="utf-8"?>
<search-key-map xmlns="http://www.idpf.org/2007/ops" xml:lang="en">
<search-key-group href="text/glossary.xhtml#foo">
<match value="foo"/>
</search-key-group>
<search-key-group href="text/glossary.xhtml#bar">
<match value="R+L=J"/>
</search-key-group>
<search-key-group href="text/glossary.xhtml#xyz">
<match value="M.O."/>
</search-key-group>
<search-key-group href="text/glossary.xhtml#abc">
<match value="’versal"/>
</search-key-group>
<search-key-group href="text/glossary.xhtml#def">
<match value="unsiker"/>
</search-key-group>
<search-key-group href="text/glossary.xhtml#ghi">
<match value="pariah">
<value value="pariahs"/>
<value value="pariahsss"/>
</match>
</search-key-group>
</search-key-map>
19 changes: 19 additions & 0 deletions tests/lint/metadata/m-070/in/src/epub/text/chapter-1.xhtml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
<?xml version="1.0" encoding="utf-8"?>
<html xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops" epub:prefix="z3998: http://www.daisy.org/z3998/2012/vocab/structure/, se: https://standardebooks.org/vocab/1.0" xml:lang="en-GB">
<head>
<title>I</title>
<link href="../css/core.css" rel="stylesheet" type="text/css"/>
<link href="../css/local.css" rel="stylesheet" type="text/css"/>
</head>
<body epub:type="bodymatter z3998:fiction">
<section id="chapter-1" epub:type="chapter">
<h2 epub:type="ordinal z3998:roman">I</h2>
<p>He ate some food.</p>
<p>A common theory was R+L=J.</p>
<p>A ’versal truth.</p>
<p>An unknown M.O.</p>
<p>Unsiker<a href="endnotes.xhtml#note-1" epub:type="noteref">1</a> is an unusual term.</p>
<p>Pariahs is plural, but should match.</p>
</section>
</body>
</html>
Loading