def test_HTMLbis(self):
data = '<em>J. David</em>'
result = [((TEXT, u'J. David'),)]
segments = []
for seg, context, offset in get_units(HTMLParser(data)):
segments.append(seg)
self.assertEqual(segments, result)
def test_surrounding_format(self):
data = '<em>Surrounding format elements should be extracted !</em>'
expected =[((TEXT,
u'Surrounding format elements should be extracted !'),)]
segments = []
for seg, context, offset in get_units(HTMLParser(data)):
segments.append(seg)
self.assertEqual(segments, expected)
def test_HTML3(self):
data = '-- toto is here -- *I am*'
result = [((TEXT, u'-- toto is here -- *I am*'),)]
segments = []
for seg, context, offset in get_units(HTMLParser(data)):
segments.append(seg)
self.assertEqual(segments, result)
def test_ignore_tags(self):
data = 'Hello <em> Baby.</em> How are you ?'
expected = [((TEXT, u'Hello '), (START_FORMAT, 1), (TEXT, u' Baby.'),
(END_FORMAT, 1)), ((TEXT, u'How are you ?'),)]
segments = []
for seg, context, offset in get_units(HTMLParser(data)):
segments.append(seg)
self.assertEqual(segments, expected)
def test_ignore_tags(self):
data = 'Hello <em> Baby.</em> How are you ?'
expected = [((TEXT, u'Hello '), (START_FORMAT, 1), (TEXT, u' Baby.'),
(END_FORMAT, 1)), ((TEXT, u'How are you ?'),)]
segments = []
for seg, context, offset in get_units(HTMLParser(data)):
segments.append(seg)
self.assertEqual(segments, expected)
def test_HTML3(self):
data = '-- toto is here -- *I am*'
result = [((TEXT, u'-- toto is here -- *I am*'),)]
segments = []
for seg, context, offset in get_units(HTMLParser(data)):
segments.append(seg)
self.assertEqual(segments, result)
def test_HTMLbis(self):
data = '<em>J. David</em>'
result = [((TEXT, u'J. David'),)]
segments = []
for seg, context, offset in get_units(HTMLParser(data)):
segments.append(seg)
self.assertEqual(segments, result)
def test_surrounding_format(self):
data = '<em>Surrounding format elements should be extracted !</em>'
expected =[((TEXT,
u'Surrounding format elements should be extracted !'),)]
segments = []
for seg, context, offset in get_units(HTMLParser(data)):
segments.append(seg)
self.assertEqual(segments, expected)
def test_HTML4(self):
data = ' <a href="http://www.debian.org/"> Debian </a> Hello. Toto'
result = [((START_FORMAT, 1), (TEXT, u' Debian '), (END_FORMAT, 1),
(TEXT, u' Hello.')), ((TEXT, u'Toto'),)]
segments = []
for seg, context, offset in get_units(HTMLParser(data)):
segments.append(seg)
self.assertEqual(segments, result)
def test_HTML(self):
data = '<a href="; t. ffff">hello </a> GOGO'
segments = []
for seg, context, offset in get_units(HTMLParser(data)):
segments.append(seg)
result = [((START_FORMAT, 1), (TEXT, u'hello '), (END_FORMAT, 1),
(TEXT, u' GOGO'))]
self.assertEqual(segments, result)
def test_HTML4(self):
data = ' <a href="http://www.debian.org/"> Debian </a> Hello. Toto'
result = [((START_FORMAT, 1), (TEXT, u' Debian '), (END_FORMAT, 1),
(TEXT, u' Hello.')), ((TEXT, u'Toto'),)]
segments = []
for seg, context, offset in get_units(HTMLParser(data)):
segments.append(seg)
self.assertEqual(segments, result)
def test_HTML(self):
data = '<a href="; t. ffff">hello </a> GOGO'
segments = []
for seg, context, offset in get_units(HTMLParser(data)):
segments.append(seg)
result = [((START_FORMAT, 1), (TEXT, u'hello '), (END_FORMAT, 1),
(TEXT, u' GOGO'))]
self.assertEqual(segments, result)
def test_paragraph(self):
"""Test formatted paragraph"""
content = ('<office:text>'
'<text:p text:style-name="Standard">'
'hello world'
'</text:p>'
'</office:text>')
content = odt_template % content
messages = XMLParser(content)
messages = [unit[0] for unit in get_units(messages)]
expected = [((TEXT, u'hello world'), )]
self.assertEqual(messages, expected)
def test_paragraph(self):
"""Test formatted paragraph"""
content = ('<office:text>'
'<text:p text:style-name="Standard">'
'hello world'
'</text:p>'
'</office:text>')
content = odt_template % content
messages = XMLParser(content)
messages = [unit[0] for unit in get_units(messages)]
expected = [((TEXT, u'hello world'),)]
self.assertEqual(messages, expected)
def test_table(self):
content = """
<office:text>
<table:table table:name="Tableau1" table:style-name="Tableau1">
<table:table-column table:style-name="Tableau1.A"
table:number-columns-repeated="3"/>
<table:table-row>
<table:table-cell table:style-name="Tableau1.A1"
office:value-type="string">
<text:p text:style-name="Table_20_Contents">A</text:p>
</table:table-cell>
<table:table-cell table:style-name="Tableau1.A1"
office:value-type="string">
<text:p text:style-name="Table_20_Contents">B</text:p>
</table:table-cell>
<table:table-cell table:style-name="Tableau1.C1"
office:value-type="string">
<text:p text:style-name="Table_20_Contents">C</text:p>
</table:table-cell>
</table:table-row>
<table:table-row>
<table:table-cell table:style-name="Tableau1.A2"
office:value-type="string">
<text:p text:style-name="Table_20_Contents">D</text:p>
</table:table-cell>
<table:table-cell table:style-name="Tableau1.A2"
office:value-type="string">
<text:p text:style-name="Table_20_Contents">E</text:p>
</table:table-cell>
<table:table-cell table:style-name="Tableau1.C2"
office:value-type="string">
<text:p text:style-name="Table_20_Contents">F</text:p>
</table:table-cell>
</table:table-row>
</table:table>
</office:text>
"""
content = odt_template % content
messages = XMLParser(content)
messages = [unit[0] for unit in get_units(messages)]
expected= [((TEXT, u'A'),),
((TEXT, u'B'),),
((TEXT, u'C'),),
((TEXT, u'D'),),
((TEXT, u'E'),),
((TEXT, u'F'),)]
self.assertEqual(messages, expected)
def test_iter_segmentation(self):
"""Here is a message surrounded by format elements and which contains
others segments. The segments must be well extracted by the iterative
algorithm."""
data = '<span>This text contains many sentences. A sentence. ' \
'Another one. This text must be well segmented. </span>'
expected = [((TEXT, u'This text contains many sentences.'),),
((TEXT, u'A sentence.'),), ((TEXT, u'Another one.'),),
((TEXT, u'This text must be well segmented.'),)]
segments = []
for seg, context, offset in get_units(HTMLParser(data)):
segments.append(seg)
self.assertEqual(segments, expected)
def test_iter_segmentation(self):
"""Here is a message surrounded by format elements and which contains
others segments. The segments must be well extracted by the iterative
algorithm."""
data = '<span>This text contains many sentences. A sentence. ' \
'Another one. This text must be well segmented. </span>'
expected = [((TEXT, u'This text contains many sentences.'),),
((TEXT, u'A sentence.'),), ((TEXT, u'Another one.'),),
((TEXT, u'This text must be well segmented.'),)]
segments = []
for seg, context, offset in get_units(HTMLParser(data)):
segments.append(seg)
self.assertEqual(segments, expected)
def test_translation_paragraph(self):
"""Test translation of an element content"""
po = POFile(string='msgctxt "paragraph"\n'
'msgid "hello world"\n'
'msgstr "hola mundo"\n')
content = ('<office:text>'
'<text:p text:style-name="Standard">'
'hello world'
'</text:p>'
'</office:text>')
content = odt_template % content
messages = XMLParser(content)
messages = translate(messages, po)
messages = [unit[0] for unit in get_units(messages)]
self.assertEqual(messages, [((TEXT, u'hola mundo'), )])
def test_translation_paragraph(self):
"""Test translation of an element content"""
po = POFile(string=
'msgctxt "paragraph"\n'
'msgid "hello world"\n'
'msgstr "hola mundo"\n')
content = ('<office:text>'
'<text:p text:style-name="Standard">'
'hello world'
'</text:p>'
'</office:text>')
content = odt_template % content
messages = XMLParser(content)
messages = translate(messages, po)
messages = [unit[0] for unit in get_units(messages)]
self.assertEqual(messages, [((TEXT, u'hola mundo'),)])
def get_units(self, srx_handler=None):
for source, context, line in get_units(self.events, srx_handler):
if len(source) > 1 or subs_expr_solo.match(source[0][1]) is None:
yield source, context, line
def get_units(self, srx_handler=None):
for filename in ['content.xml', 'meta.xml', 'styles.xml']:
events = self.get_events(filename)
for message in get_units(events, srx_handler):
# FIXME the line number has no sense here
yield message
def get_units(self, srx_handler=None):
for filename in ['content.xml', 'meta.xml', 'styles.xml']:
events = self.get_events(filename)
for message in get_units(events, srx_handler):
# FIXME the line number has no sense here
yield message
def get_units(self, srx_handler=None):
for source, context, line in get_units(self.events, srx_handler):
if len(source) > 1 or subs_expr_solo.match(source[0][1]) is None:
yield source, context, line