def test_xml_lmf_write(self):
import sys, os
# Create LMF objects
lexical_entry = LexicalEntry()
lexical_entry.lemma = Lemma()
lexical_entry.partOfSpeech = "toto"
lexical_entry.status = "draft"
lexical_entry.lemma.lexeme = "hello"
# Write XML LMF file and test result
utest_path = sys.path[0] + '/'
xml_lmf_filename = utest_path + "lmf_output.xml"
xml_lmf_write(lexical_entry, xml_lmf_filename)
xml_lmf_file = open(xml_lmf_filename, "r")
expected_lines = [
"""<?xml version="1.0" encoding="utf-8"?>""" + EOL,
"""<LexicalEntry id="0">""" + EOL,
""" <feat att="status" val="draft"/>""" + EOL,
""" <Lemma>""" + EOL,
""" <feat att="lexeme" val="hello"/>""" + EOL,
""" </Lemma>""" + EOL,
""" <feat att="partOfSpeech" val="toto"/>""" + EOL,
"""</LexicalEntry>""" + EOL
]
self.assertListEqual(expected_lines, xml_lmf_file.readlines())
xml_lmf_file.close()
del lexical_entry.lemma
lexical_entry.lemma = None
del lexical_entry
# Remove XML LMF file
os.remove(xml_lmf_filename)
def set_spelling_variant(self, spelling_variant):
"""! @brief Set spelling variant.
Attribute 'spellingVariant' is owned by FormRepresentation, which is owned by Lemma.
@param spelling_variant The spelling variant to set.
@return LexicalEntry instance.
"""
# Create a Lemma instance if not yet created
if self.lemma is None:
self.lemma = Lemma()
self.lemma.set_spelling_variant(spelling_variant)
return self
def set_contextual_variation(self, contextual_variation):
"""! @brief Set contextual variation.
Attribute 'contextualVariation' is owned by FormRepresentation, which is owned by Lemma.
@param contextual_variation The contextual variation to set.
@return LexicalEntry instance.
"""
# Create a Lemma instance if not yet created
if self.lemma is None:
self.lemma = Lemma()
self.lemma.set_contextual_variation(contextual_variation)
return self
def set_transliteration(self, transliteration):
"""! @brief Set transliteration.
Attribute 'transliteration' is owned by FormRepresentation, which is owned by Lemma.
@param transliteration The transliteration to set.
@return LexicalEntry instance.
"""
# Create a Lemma instance if not yet created
if self.lemma is None:
self.lemma = Lemma()
self.lemma.set_transliteration(transliteration)
return self
def set_tone(self, tone):
"""! @brief Set tone.
Attribute 'tone' is owned by FormRepresentation, which is owned by Lemma.
@param tone The tone to set.
@return LexicalEntry instance.
"""
# Create a Lemma instance if not yet created
if self.lemma is None:
self.lemma = Lemma()
self.lemma.set_tone(tone)
return self
def set_lexeme(self, lexeme):
"""! @brief Set lexeme.
Attribute 'lexeme' is owned by Lemma.
@param lexeme The lexeme to set.
@return LexicalEntry instance.
"""
# Create a Lemma instance if not yet created
if self.lemma is None:
self.lemma = Lemma()
self.lemma.set_lexeme(lexeme)
return self
def set_script_name(self, script_name):
"""! @brief Set script name.
Attribute 'scriptName' is owned by FormRepresentation, which is owned by Lemma.
@param script_name The script name to set.
@return LexicalEntry instance.
"""
# Create a Lemma instance if not yet created
if self.lemma is None:
self.lemma = Lemma()
self.lemma.set_script_name(script_name)
return self
def set_dialect(self, dialect):
"""! @brief Set dialect.
Attribute 'dialect' is owned by FormRepresentation, which is owned by Lemma.
@param dialect The dialect to set.
@return LexicalEntry instance.
"""
# Create a Lemma instance if not yet created
if self.lemma is None:
self.lemma = Lemma()
self.lemma.set_dialect(dialect)
return self
def set_geographical_variant(self, geographical_variant):
"""! @brief Set geographical variant.
Attribute 'geographicalVariant' is owned by FormRepresentation, which is owned by Lemma.
@param geographical_variant The geographical variant to set.
@return LexicalEntry instance.
"""
# Create a Lemma instance if not yet created
if self.lemma is None:
self.lemma = Lemma()
self.lemma.set_geographical_variant(geographical_variant)
return self
def set_citation_form(self, citation_form, script_name=None):
"""! @brief Set citation form.
Attribute 'citationForm' is owned by FormRepresentation, which is owned by Lemma.
@param citation_form The citation form to set.
@param script_name The name of the script used to write the citation form, e.g. devanagari.
@return LexicalEntry instance.
"""
# Create a Lemma instance if not yet created
if self.lemma is None:
self.lemma = Lemma()
self.lemma.set_citation_form(citation_form, script_name)
return self
def set_phonetic_form(self, phonetic_form, script_name=None):
"""! @brief Set phonetic form.
Attribute 'phoneticForm' is owned by FormRepresentation, which is owned by Lemma.
@param phonetic_form The phonetic form to set.
@param script_name The name of the script used to write the phonetic form, e.g. pinyin.
@return LexicalEntry instance.
"""
# Create a Lemma instance if not yet created
if self.lemma is None:
self.lemma = Lemma()
self.lemma.set_phonetic_form(phonetic_form, script_name)
return self
def set_variant_comment(self, comment, language=None):
"""! @brief Set variant comment and language.
Attributes 'comment' and 'language' are owned by FormRepresentation, which is owned by Lemma.
@param comment Variant comment.
@param language Language of comment.
@return LexicalEntry instance.
"""
# Create a Lemma instance if not yet created
if self.lemma is None:
self.lemma = Lemma()
self.lemma.set_variant_comment(comment, language)
return self
def set_variant_form(self, variant_form, type="unspecified"):
"""! @brief Set variant form and type.
Attributes 'variantForm' and 'type' are owned by FormRepresentation, which is owned by Lemma.
@param variant_form Variant form.
@param type Type of variant, in range 'type_variant_range' defined in 'common/range.py'.
@return LexicalEntry instance.
"""
# Create a Lemma instance if not yet created
if self.lemma is None:
self.lemma = Lemma()
self.lemma.set_variant_form(variant_form, type)
return self
def set_audio(self, media_type="audio", file_name=None, author=None, quality=None, start_position="T00:00:00", duration=None, external_reference=None, audio_file_format=None):
"""! @brief Set audio resource.
Attributes 'mediaType', 'fileName', 'author', 'quality', 'startPosition', 'durationOfEffectiveSpeech', 'externalReference', 'audioFileFormat' are owned by Material/Audio, which is owned by FormRepresentation, itself owend by Lemma.
@param media_type The media type to set.
@param file_name Name of the audio file.
@param author Author of the recording.
@param quality Quality of the recording, in range 'quality_range' defined in 'common/range.py'.
@param start_position Start position of the form in the recording, in format 'Thh:mm:ss,msms', e.g. "T00:05:00".
@param duration Duration of the effcetive speech, in format 'PThhHmmMssS', e.g. "PT00:05:00".
@param external_reference Reference of the audio file, if not directly provided.
@param audio_file_format Format of the audio file, e.g. "wav".
@return LexicalEntry instance.
"""
# Create a Lemma instance if not yet created
if self.lemma is None:
self.lemma = Lemma()
self.lemma.set_audio(media_type, file_name, author, quality, start_position, duration, external_reference, audio_file_format)
return self
def test_mdf_write(self):
import sys, os
# Create LMF objects
lexical_entry = LexicalEntry()
lexical_entry.lemma = Lemma()
lexical_entry.partOfSpeech = "toto"
lexical_entry.status = "draft"
lexical_entry.lemma.lexeme = "hello"
lexicon = Lexicon()
lexicon.add_lexical_entry(lexical_entry)
# Write MDF file and test result
utest_path = sys.path[0] + '/'
mdf_filename = utest_path + "output.txt"
mdf_write(lexicon, mdf_filename)
mdf_file = open(mdf_filename, "r")
expected_lines = [
"\\lx hello" + EOL, "\\ps toto" + EOL, "\\st draft" + EOL, EOL
]
self.assertListEqual(expected_lines, mdf_file.readlines())
mdf_file.close()
# Customize mapping
lmf2mdf = dict({
"lx":
lambda lexical_entry: lexical_entry.get_status(),
"ps":
lambda lexical_entry: lexical_entry.get_partOfSpeech(),
"st":
lambda lexical_entry: lexical_entry.get_lexeme()
})
order = ["st", "lx", "ps"]
# Write MDF file and test result
mdf_write(lexicon, mdf_filename, lmf2mdf, order)
mdf_file = open(mdf_filename, "r")
expected_lines = [
"\\st hello" + EOL, "\\lx draft" + EOL, "\\ps toto" + EOL, EOL
]
self.assertListEqual(expected_lines, mdf_file.readlines())
mdf_file.close()
del lexical_entry.lemma
lexical_entry.lemma = None
del lexical_entry, lexicon
# Remove MDF file
os.remove(mdf_filename)
def test_build_sub_elements(self):
# Create LMF objects and an empty XML element
instance = LexicalEntry()
instance.lemma = Lemma()
instance.partOfSpeech = "toto"
instance.status = "draft"
instance.lemma.lexeme = "hello"
element = Element("LexicalEntry")
# Build sub-elements and test result
build_sub_elements(instance, element)
lemma = element.find("Lemma")
lexeme = lemma.find("feat")
self.assertEqual(lexeme.attrib["att"], "lexeme")
self.assertEqual(lexeme.attrib["val"], "hello")
[status, partOfSpeech] = element.findall("feat")
self.assertEqual(partOfSpeech.attrib["att"], "partOfSpeech")
self.assertEqual(partOfSpeech.attrib["val"], "toto")
self.assertEqual(status.attrib["att"], "status")
self.assertEqual(status.attrib["val"], "draft")
del instance.lemma
instance.lemma = None
del instance, element
def test_doc_write(self):
import sys, os
# Create LMF objects
lexical_entry = LexicalEntry()
lexical_entry.lemma = Lemma()
lexical_entry.partOfSpeech = "toto"
lexical_entry.status = "draft"
lexical_entry.lemma.lexeme = "hello"
lexicon = Lexicon()
lexicon.add_lexical_entry(lexical_entry)
lexical_resource = LexicalResource()
lexical_resource.add_lexicon(lexicon)
# Write document file and test result
utest_path = sys.path[0] + '/'
doc_filename = utest_path + "output.docx"
doc_write(lexical_resource, doc_filename)
doc_file = open(doc_filename, "r")
doc_file.readlines()
doc_file.close()
# Customize mapping
def lmf2doc(lexicon, document, items, sort_order, paradigms, reverse):
return "test"
# Write document file and test result
doc_write(lexical_resource, doc_filename, None, lmf2doc)
doc_file = open(doc_filename, "r")
doc_file.readlines()
doc_file.close()
del lexical_entry.lemma
lexical_entry.lemma = None
del lexical_entry, lexicon
lexicon = None
del lexical_resource
# Remove document file
os.remove(doc_filename)
def test_tex_write(self):
import sys, os
# Create LMF objects
lexical_entry = LexicalEntry()
lexical_entry.lemma = Lemma()
lexical_entry.partOfSpeech = "toto"
lexical_entry.status = "draft"
lexical_entry.lemma.lexeme = "hello"
lexicon = Lexicon()
lexicon.add_lexical_entry(lexical_entry)
lexical_resource = LexicalResource()
lexical_resource.add_lexicon(lexicon)
# Write LaTeX file and test result
utest_path = sys.path[0] + '/'
tex_filename = utest_path + "output.tex"
tex_write(lexical_resource, tex_filename)
tex_file = open(tex_filename, "r")
begin_lines = [
EOL, "\\begin{document}" + EOL, "\\maketitle" + EOL,
"\\newpage" + EOL, EOL,
"\\def\\mytextsc{\\bgroup\\obeyspaces\\mytextscaux}" + EOL,
"\\def\\mytextscaux#1{\\mytextscauxii #1\\relax\\relax\\egroup}" +
EOL, "\\def\\mytextscauxii#1{%" + EOL,
"\\ifx\\relax#1\\else \\ifcat#1\\@sptoken{} \\expandafter\\expandafter\\expandafter\\mytextscauxii\\else"
+ EOL,
"\\ifnum`#1=\\uccode`#1 {\\normalsize #1}\\else {\\footnotesize \\uppercase{#1}}\\fi \\expandafter\\expandafter\\expandafter\\mytextscauxii\\expandafter\\fi\\fi}"
+ EOL, EOL, "\\setlength\\parindent{0cm}" + EOL, EOL,
"\\addmediapath{.}" + EOL, "\\addmediapath{./mp3}" + EOL,
"\\addmediapath{./wav}" + EOL, "\\graphicspath{{" +
os.path.abspath('.') + "/pylmflib/output/img/}}" + EOL, EOL,
"\\newpage" + EOL, "\\begin{multicols}{2}" + EOL, EOL
]
end_lines = ["\end{multicols}" + EOL, "\end{document}" + EOL]
expected_lines = [
"\\newpage" + EOL,
"\\section*{\\centering- \\textbf{\ipa{H}} \\textbf{\ipa{h}} -}" +
EOL,
#"\\pdfbookmark[1]{\ipa{ H h }}{ H h }" + EOL,
"\\paragraph{\\hspace{-0.5cm} \\textbf{\ipa{hello}}} \\hypertarget{01}{}"
+ EOL,
"\markboth{\\textbf{\\ipa{hello}}}{}" + EOL,
"\\textit{Status:} draft" + EOL,
"\lhead{\\firstmark}" + EOL,
"\\rhead{\\botmark}" + EOL,
EOL
]
self.assertListEqual(begin_lines + expected_lines + end_lines,
tex_file.readlines())
tex_file.close()
# Customize mapping
my_lmf_tex = dict({
"Lemma.lexeme":
lambda lexical_entry: "is " + lexical_entry.get_lexeme(
) + "." + EOL,
"LexicalEntry.id":
lambda lexical_entry: "The lexical entry " + str(lexical_entry.
get_id()) + " ",
"LexicalEntry.partOfSpeech":
lambda lexical_entry: "Its grammatical category is " +
lexical_entry.get_partOfSpeech() + "." + EOL,
"LexicalEntry.status":
lambda lexical_entry: "Warning: " + lexical_entry.get_status(
) + " version!" + EOL
})
my_order = [
"LexicalEntry.id", "Lemma.lexeme", "LexicalEntry.partOfSpeech",
"LexicalEntry.status"
]
def lmf2tex(entry, font):
result = ""
for attribute in my_order:
result += my_lmf_tex[attribute](entry)
return result
# Write LaTeX file and test result
tex_write(lexical_resource, tex_filename, None, None, lmf2tex, font)
tex_file = open(tex_filename, "r")
expected_lines = [
"\\newpage" + EOL,
"\\section*{\\centering- \\textbf{\ipa{H}} \\textbf{\ipa{h}} -}" +
EOL,
#"\\pdfbookmark[1]{\ipa{ H h }}{ H h }" + EOL,
"The lexical entry 01 is hello." + EOL,
"Its grammatical category is toto." + EOL,
"Warning: draft version!" + EOL,
"\lhead{\\firstmark}" + EOL,
"\\rhead{\\botmark}" + EOL,
EOL
]
self.assertListEqual(begin_lines + expected_lines + end_lines,
tex_file.readlines())
tex_file.close()
del lexical_entry.lemma
lexical_entry.lemma = None
del lexical_entry, lexicon
lexicon = None
del lexical_resource
# Remove LaTeX file
os.remove(tex_filename)
def setUp(self):
# Instantiate a Lemma object
self.lemma = Lemma()