def build_notes(book):
task_logger.info(book.slug)
with transaction.atomic():
book.notesource_set.all().delete()
if book.html_file:
from librarian import html
from librarian.fn_qualifiers import FN_QUALIFIERS
for anchor, fn_type, qualifiers, text_str, html_str in \
html.extract_annotations(book.html_file.path):
sort_key = sortify(text_str).strip()[:128]
language = book.language
notes = Note.objects.filter(sort_key=sort_key, fn_type=fn_type, language=language, html=html_str)
if notes:
note = notes[0]
else:
note = Note.objects.create(
sort_key=sort_key,
html=html_str,
fn_type=fn_type,
language=language
)
qualifier_objects = []
for qualifier in qualifiers:
obj, created = Qualifier.objects.get_or_create(
qualifier=qualifier, defaults={
'name': FN_QUALIFIERS.get(qualifier, '')
})
qualifier_objects.append(obj)
note.qualifiers = qualifier_objects
note.notesource_set.create(book=book, anchor=anchor)
Note.objects.filter(notesource=None).delete()
def build_notes(book):
task_logger.info(book.slug)
with transaction.atomic():
book.notesource_set.all().delete()
if book.html_file:
from librarian import html
from librarian.fn_qualifiers import FN_QUALIFIERS
for anchor, fn_type, qualifiers, text_str, html_str in \
html.extract_annotations(book.html_file.path):
sort_key = sortify(text_str).strip()[:128]
language = book.language
notes = Note.objects.filter(sort_key=sort_key,
fn_type=fn_type,
language=language,
html=html_str)
if notes:
note = notes[0]
else:
note = Note.objects.create(sort_key=sort_key,
html=html_str,
fn_type=fn_type,
language=language)
qualifier_objects = []
for qualifier in qualifiers:
obj, created = Qualifier.objects.get_or_create(
qualifier=qualifier,
defaults={'name': FN_QUALIFIERS.get(qualifier, '')})
qualifier_objects.append(obj)
note.qualifiers = qualifier_objects
note.notesource_set.create(book=book, anchor=anchor)
Note.objects.filter(notesource=None).delete()
def build_notes(book):
Note.objects.filter(book=book).delete()
if book.html_file:
from librarian import html
for anchor, text_str, html_str in html.extract_annotations(book.html_file.path):
Note.objects.create(book=book, anchor=anchor,
html=html_str,
sort_key=sortify(text_str).strip()[:128])
def build_notes(book):
Note.objects.filter(book=book).delete()
if book.html_file:
from librarian import html
for anchor, text_str, html_str in html.extract_annotations(
book.html_file.path):
Note.objects.create(book=book,
anchor=anchor,
html=html_str,
sort_key=sortify(text_str).strip()[:128])
def test_annotations():
annotations = (
('<pe/>', ('pe', [], '', '<p></p>'), 'Empty footnote'),
('<pr>Definiendum --- definiens.</pr>',
('pr', [], 'Definiendum \u2014 definiens.',
'<p>Definiendum \u2014 definiens.</p>'), 'Plain footnote.'),
('<pt><slowo_obce>Definiendum</slowo_obce> --- definiens.</pt>',
('pt', [], 'Definiendum \u2014 definiens.',
'<p><em class="foreign-word">Definiendum</em> \u2014 definiens.</p>'
), 'Standard footnote.'),
('<pr>Definiendum (łac.) --- definiens.</pr>',
('pr', ['łac.'], 'Definiendum (łac.) \u2014 definiens.',
'<p>Definiendum (łac.) \u2014 definiens.</p>'),
'Plain footnote with qualifier'),
('<pe><slowo_obce>Definiendum</slowo_obce> (łac.) --- definiens.</pe>',
('pe', ['łac.'], 'Definiendum (łac.) \u2014 definiens.',
'<p><em class="foreign-word">Definiendum</em> (łac.) \u2014 definiens.</p>'
), 'Standard footnote with qualifier.'),
('<pt> <slowo_obce>Definiendum</slowo_obce> (daw.) --- definiens.</pt>',
('pt', ['daw.'], 'Definiendum (daw.) \u2014 definiens.',
'<p> <em class="foreign-word">Definiendum</em> (daw.) \u2014 definiens.</p>'
), 'Standard footnote with leading whitespace and qualifier.'),
('<pr>Definiendum (łac.) --- <slowo_obce>definiens</slowo_obce>.</pr>',
('pr', ['łac.'], 'Definiendum (łac.) \u2014 definiens.',
'<p>Definiendum (łac.) \u2014 <em class="foreign-word">definiens</em>.</p>'
), 'Plain footnote with qualifier and some emphasis.'),
('<pe><slowo_obce>Definiendum</slowo_obce> (łac.) --- <slowo_obce>definiens</slowo_obce>.</pe>',
('pe', ['łac.'], 'Definiendum (łac.) \u2014 definiens.',
'<p><em class="foreign-word">Definiendum</em> (łac.) \u2014 <em class="foreign-word">definiens</em>.</p>'
), 'Standard footnote with qualifier and some emphasis.'),
('<pe>Definiendum (łac.) --- definiens (some) --- more text.</pe>', (
'pe',
['łac.'],
'Definiendum (łac.) \u2014 definiens (some) \u2014 more text.',
'<p>Definiendum (łac.) \u2014 definiens (some) \u2014 more text.</p>',
), 'Footnote with a second parentheses and mdash.'),
('<pe><slowo_obce>gemajna</slowo_obce> (daw., z niem. <slowo_obce>gemein</slowo_obce>: zwykły) --- '
'częściej: gemajn, szeregowiec w wojsku polskim cudzoziemskiego autoramentu.</pe>',
('pe', ['daw.', 'niem.'],
'gemajna (daw., z niem. gemein: zwykły) \u2014 częściej: gemajn, '
'szeregowiec w wojsku polskim cudzoziemskiego autoramentu.',
'<p><em class="foreign-word">gemajna</em> (daw., z niem. <em class="foreign-word">gemein</em>: zwykły) '
'\u2014 częściej: gemajn, szeregowiec w wojsku polskim cudzoziemskiego autoramentu.</p>'
), 'Footnote with multiple and qualifiers and emphasis.'),
)
xml_src = '''<utwor><akap> %s </akap></utwor>''' % "".join(
t[0] for t in annotations)
html = WLDocument.from_string(xml_src,
parse_dublincore=False).as_html().get_file()
res_annotations = list(extract_annotations(html))
for i, (src, expected, name) in enumerate(annotations):
yield _test_annotation, expected, res_annotations[i], name
def test_annotations():
annotations = (
("<pe/>", ("pe", [], "", "<p></p>"), "Empty footnote"),
(
"<pr>Definiendum --- definiens.</pr>",
("pr", [], "Definiendum \u2014 definiens.", "<p>Definiendum \u2014 definiens.</p>"),
"Plain footnote.",
),
(
"<pt><slowo_obce>Definiendum</slowo_obce> --- definiens.</pt>",
(
"pt",
[],
"Definiendum \u2014 definiens.",
'<p><em class="foreign-word">Definiendum</em> \u2014 definiens.</p>',
),
"Standard footnote.",
),
(
"<pr>Definiendum (łac.) --- definiens.</pr>",
("pr", ["łac."], "Definiendum (łac.) \u2014 definiens.", "<p>Definiendum (łac.) \u2014 definiens.</p>"),
"Plain footnote with qualifier",
),
(
"<pe><slowo_obce>Definiendum</slowo_obce> (łac.) --- definiens.</pe>",
(
"pe",
["łac."],
"Definiendum (łac.) \u2014 definiens.",
'<p><em class="foreign-word">Definiendum</em> (łac.) \u2014 definiens.</p>',
),
"Standard footnote with qualifier.",
),
(
"<pt> <slowo_obce>Definiendum</slowo_obce> (daw.) --- definiens.</pt>",
(
"pt",
["daw."],
"Definiendum (daw.) \u2014 definiens.",
'<p> <em class="foreign-word">Definiendum</em> (daw.) \u2014 definiens.</p>',
),
"Standard footnote with leading whitespace and qualifier.",
),
(
"<pr>Definiendum (łac.) --- <slowo_obce>definiens</slowo_obce>.</pr>",
(
"pr",
["łac."],
"Definiendum (łac.) \u2014 definiens.",
'<p>Definiendum (łac.) \u2014 <em class="foreign-word">definiens</em>.</p>',
),
"Plain footnote with qualifier and some emphasis.",
),
(
"<pe><slowo_obce>Definiendum</slowo_obce> (łac.) --- <slowo_obce>definiens</slowo_obce>.</pe>",
(
"pe",
["łac."],
"Definiendum (łac.) \u2014 definiens.",
'<p><em class="foreign-word">Definiendum</em> (łac.) \u2014 <em class="foreign-word">definiens</em>.</p>',
),
"Standard footnote with qualifier and some emphasis.",
),
(
"<pe>Definiendum (łac.) --- definiens (some) --- more text.</pe>",
(
"pe",
["łac."],
"Definiendum (łac.) \u2014 definiens (some) \u2014 more text.",
"<p>Definiendum (łac.) \u2014 definiens (some) \u2014 more text.</p>",
),
"Footnote with a second parentheses and mdash.",
),
(
"<pe><slowo_obce>gemajna</slowo_obce> (daw., z niem. <slowo_obce>gemein</slowo_obce>: zwykły) --- częściej: gemajn, szeregowiec w wojsku polskim cudzoziemskiego autoramentu.</pe>",
(
"pe",
["daw.", "niem."],
"gemajna (daw., z niem. gemein: zwykły) \u2014 częściej: gemajn, szeregowiec w wojsku polskim cudzoziemskiego autoramentu.",
'<p><em class="foreign-word">gemajna</em> (daw., z niem. <em class="foreign-word">gemein</em>: zwykły) \u2014 częściej: gemajn, szeregowiec w wojsku polskim cudzoziemskiego autoramentu.</p>',
),
"Footnote with multiple and qualifiers and emphasis.",
),
)
xml_src = """<utwor><akap> %s </akap></utwor>""" % "".join(t[0] for t in annotations)
html = WLDocument.from_string(xml_src, parse_dublincore=False).as_html().get_file()
res_annotations = list(extract_annotations(html))
for i, (src, expected, name) in enumerate(annotations):
yield _test_annotation, expected, res_annotations[i], name
def test_annotations():
annotations = (
('<pe/>', (
'pe',
[],
'',
'<p></p>'
),
'Empty footnote'),
('<pr>Definiendum --- definiens.</pr>', (
'pr',
[],
'Definiendum \u2014 definiens.',
'<p>Definiendum \u2014 definiens.</p>'
),
'Plain footnote.'),
('<pt><slowo_obce>Definiendum</slowo_obce> --- definiens.</pt>', (
'pt',
[],
'Definiendum \u2014 definiens.',
'<p><em class="foreign-word">Definiendum</em> \u2014 definiens.</p>'
),
'Standard footnote.'),
('<pr>Definiendum (łac.) --- definiens.</pr>', (
'pr',
['łac.'],
'Definiendum (łac.) \u2014 definiens.',
'<p>Definiendum (łac.) \u2014 definiens.</p>'
),
'Plain footnote with qualifier'),
('<pe><slowo_obce>Definiendum</slowo_obce> (łac.) --- definiens.</pe>', (
'pe',
['łac.'],
'Definiendum (łac.) \u2014 definiens.',
'<p><em class="foreign-word">Definiendum</em> (łac.) \u2014 definiens.</p>'
),
'Standard footnote with qualifier.'),
('<pt> <slowo_obce>Definiendum</slowo_obce> (daw.) --- definiens.</pt>', (
'pt',
['daw.'],
'Definiendum (daw.) \u2014 definiens.',
'<p> <em class="foreign-word">Definiendum</em> (daw.) \u2014 definiens.</p>'
),
'Standard footnote with leading whitespace and qualifier.'),
('<pr>Definiendum (łac.) --- <slowo_obce>definiens</slowo_obce>.</pr>', (
'pr',
['łac.'],
'Definiendum (łac.) \u2014 definiens.',
'<p>Definiendum (łac.) \u2014 <em class="foreign-word">definiens</em>.</p>'
),
'Plain footnote with qualifier and some emphasis.'),
('<pe><slowo_obce>Definiendum</slowo_obce> (łac.) --- <slowo_obce>definiens</slowo_obce>.</pe>', (
'pe',
['łac.'],
'Definiendum (łac.) \u2014 definiens.',
'<p><em class="foreign-word">Definiendum</em> (łac.) \u2014 <em class="foreign-word">definiens</em>.</p>'
),
'Standard footnote with qualifier and some emphasis.'),
('<pe>Definiendum (łac.) --- definiens (some) --- more text.</pe>', (
'pe',
['łac.'],
'Definiendum (łac.) \u2014 definiens (some) \u2014 more text.',
'<p>Definiendum (łac.) \u2014 definiens (some) \u2014 more text.</p>',
),
'Footnote with a second parentheses and mdash.'),
('<pe><slowo_obce>gemajna</slowo_obce> (daw., z niem. <slowo_obce>gemein</slowo_obce>: zwykły) --- '
'częściej: gemajn, szeregowiec w wojsku polskim cudzoziemskiego autoramentu.</pe>', (
'pe',
['daw.', 'niem.'],
'gemajna (daw., z niem. gemein: zwykły) \u2014 częściej: gemajn, '
'szeregowiec w wojsku polskim cudzoziemskiego autoramentu.',
'<p><em class="foreign-word">gemajna</em> (daw., z niem. <em class="foreign-word">gemein</em>: zwykły) '
'\u2014 częściej: gemajn, szeregowiec w wojsku polskim cudzoziemskiego autoramentu.</p>'
),
'Footnote with multiple and qualifiers and emphasis.'),
)
xml_src = '''<utwor><akap> %s </akap></utwor>''' % "".join(
t[0] for t in annotations)
html = WLDocument.from_string(xml_src, parse_dublincore=False).as_html().get_file()
res_annotations = list(extract_annotations(html))
for i, (src, expected, name) in enumerate(annotations):
yield _test_annotation, expected, res_annotations[i], name
def test_annotations():
annotations = (
('<pe/>', (
'pe',
None,
'',
'<p></p>'
),
'Empty footnote'),
(
'<pr>Definiendum --- definiens.</pr>', (
'pr',
None,
'Definiendum \u2014 definiens.',
'<p>Definiendum \u2014 definiens.</p>'
),
'Plain footnote.'),
('<pt><slowo_obce>Definiendum</slowo_obce> --- definiens.</pt>', (
'pt',
None,
'Definiendum \u2014 definiens.',
'<p><em class="foreign-word">Definiendum</em> \u2014 definiens.</p>'
),
'Standard footnote.'),
('<pr>Definiendum (łac.) --- definiens.</pr>', (
'pr',
'łac.',
'Definiendum (łac.) \u2014 definiens.',
'<p>Definiendum (łac.) \u2014 definiens.</p>'
),
'Plain footnote with qualifier'),
('<pe><slowo_obce>Definiendum</slowo_obce> (łac.) --- definiens.</pe>', (
'pe',
'łac.',
'Definiendum (łac.) \u2014 definiens.',
'<p><em class="foreign-word">Definiendum</em> (łac.) \u2014 definiens.</p>'
),
'Standard footnote with qualifier.'),
('<pt> <slowo_obce>Definiendum</slowo_obce> (daw.) --- definiens.</pt>', (
'pt',
'daw.',
'Definiendum (daw.) \u2014 definiens.',
'<p> <em class="foreign-word">Definiendum</em> (daw.) \u2014 definiens.</p>'
),
'Standard footnote with leading whitespace and qualifier.'),
('<pr>Definiendum (łac.) --- <slowo_obce>definiens</slowo_obce>.</pr>', (
'pr',
'łac.',
'Definiendum (łac.) \u2014 definiens.',
'<p>Definiendum (łac.) \u2014 <em class="foreign-word">definiens</em>.</p>'
),
'Plain footnote with qualifier and some emphasis.'),
('<pe><slowo_obce>Definiendum</slowo_obce> (łac.) --- <slowo_obce>definiens</slowo_obce>.</pe>', (
'pe',
'łac.',
'Definiendum (łac.) \u2014 definiens.',
'<p><em class="foreign-word">Definiendum</em> (łac.) \u2014 <em class="foreign-word">definiens</em>.</p>'
),
'Standard footnote with qualifier and some emphasis.'),
('<pe>Definiendum (łac.) --- definiens (some) --- more text.</pe>', (
'pe',
'łac.',
'Definiendum (łac.) \u2014 definiens (some) \u2014 more text.',
'<p>Definiendum (łac.) \u2014 definiens (some) \u2014 more text.</p>',
),
'Footnote with a second parentheses and mdash.'),
)
xml_src = '''<utwor><akap> %s </akap></utwor>''' % "".join(
t[0] for t in annotations)
html = WLDocument.from_string(xml_src, parse_dublincore=False).as_html().get_file()
res_annotations = list(extract_annotations(html))
for i, (src, expected, name) in enumerate(annotations):
yield _test_annotation, expected, res_annotations[i], name
