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_odt_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] + '/'
odt_filename = utest_path + "output.odt"
odt_write(lexical_resource, odt_filename)
odt_file = open(odt_filename, "r")
odt_file.readlines()
odt_file.close()
# Customize mapping
def lmf2odt(lexicon, document, items, sort_order, paradigms, reverse):
return "test"
# Write document file and test result
odt_write(lexical_resource, odt_filename, None, lmf2odt)
odt_file = open(odt_filename, "r")
odt_file.readlines()
odt_file.close()
del lexical_entry.lemma
lexical_entry.lemma = None
del lexical_entry, lexicon
lexicon = None
del lexical_resource
# Remove document file
os.remove(odt_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 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 config_read(filename):
"""! @brief Read an XML file giving the user configuration.
@param filename The name of the XML file to read with full path, for instance 'pylmflib/pylmflib/config/default/config.xml'.
@return A Lexical Resource.
"""
import os
import config.xml
configuration = parse_xml(filename)
# Parse XML elements
for format in configuration:
if format.tag == "Language":
# XML element "Language" have several XML subelements "lang"
for lang in format:
# XML elements "lang" have 2 XML attributes: one for the nature of the language ("att"), a second for the language code ("val")
exec("config.xml." + lang.attrib["att"] + " = '" + lang.attrib["val"] + "'")
elif format.tag == "Font":
config.xml.font = dict()
# XML element "Font" have several XML subelements "font"
for font in format:
# XML elements "font" have 2 XML attributes: one for the nature of the language ("att"), a second for the variable name ("var")
exec("l = lambda " + font.attrib['var'] + ": " + font.text)
config.xml.font.update({font.attrib['att']: l})
elif format.tag == "LMF":
# Create lexical resource and set DTD version
lexical_resource = LexicalResource(format[0].attrib["dtdVersion"])
for object in format[0]:
if object.tag == "GlobalInformation":
# Set global information
for feat in object:
if feat.attrib["att"] == "languageCode":
lexical_resource.set_language_code(feat.attrib["val"])
elif feat.attrib["att"] == "author":
lexical_resource.set_author(feat.attrib["val"])
elif feat.attrib["att"] == "version":
lexical_resource.set_version(feat.attrib["val"])
elif feat.attrib["att"] == "lastUpdate":
lexical_resource.set_last_update(feat.attrib["val"])
elif feat.attrib["att"] == "license":
lexical_resource.set_license(feat.attrib["val"])
elif feat.attrib["att"] == "characterEncoding":
lexical_resource.set_character_encoding(feat.attrib["val"])
elif feat.attrib["att"] == "dateCoding":
lexical_resource.set_date_coding(feat.attrib["val"])
elif feat.attrib["att"] == "creationDate":
lexical_resource.set_creation_date(feat.attrib["val"])
elif feat.attrib["att"] == "projectName":
lexical_resource.set_project_name(feat.attrib["val"])
elif feat.attrib["att"] == "description":
lexical_resource.set_description(feat.attrib["val"])
elif object.tag == "Lexicon":
# Create lexicon and set identifier
lexicon = Lexicon(object.attrib["id"])
# Set lexicon attributes
for feat in object:
if feat.attrib["att"] == "language":
lexicon.set_language(feat.attrib["val"])
elif feat.attrib["att"] == "languageScript":
lexicon.set_languageScript(feat.attrib["val"])
elif feat.attrib["att"] == "label":
lexicon.set_label(feat.attrib["val"])
elif feat.attrib["att"] == "lexiconType":
lexicon.set_lexiconType(feat.attrib["val"])
elif feat.attrib["att"] == "entrySource":
lexicon.set_entrySource(feat.attrib["val"])
elif feat.attrib["att"] == "localPath":
lexicon.set_localPath(feat.attrib["val"])
# Set absolute path to audio files
config.xml.audio_path = os.path.abspath(os.path.abspath('.') + "/" + feat.attrib["val"]) + "/"
# Attach lexicon to the lexical resource
lexical_resource.add_lexicon(lexicon)
elif format.tag == "MDF":
for mdf in format:
if mdf.tag == "mdf_lmf":
# XML elements "mdf_lmf" have 2 XML attributes: one for the name of the marker ("marker"), a second for the variable name ("var")
exec("l = lambda " + mdf.attrib['var'] + ": " + mdf.text)
mdf_lmf.update({mdf.attrib['marker']: l})
elif mdf.tag == "ps_partOfSpeech":
# XML elements "ps_partOfSpeech" have 2 XML attributes: one for the MDF value ("ps"), a second for the LMF value ("partOfSpeech")
ps_partOfSpeech.update({mdf.attrib['ps']: mdf.attrib['partOfSpeech']})
# Also automatically update range of possible values allowed for LMF part of speech LexicalEntry attribute -->
partOfSpeech_range.add(mdf.attrib['partOfSpeech'])
# And automatically update the reverse operation
partOfSpeech_tex.update({mdf.attrib['partOfSpeech']: mdf.attrib['ps']})
elif mdf.tag == "pdl_paradigmLabel":
# XML elements "pdl_paradigmLabel" have 2 XML attributes: one for the MDF value ("pdl"), a second for the LMF value ("paradigmLabel")
pdl_paradigmLabel.update({mdf.attrib['pdl']: mdf.attrib['paradigmLabel']})
# Also automatically update range of possible values allowed for LMF paradigm label Paradigm attribute -->
paradigmLabel_range.add(mdf.attrib['paradigmLabel'])
# And automatically update the reverse operation
paradigmLabel_tex.update({mdf.attrib['paradigmLabel']: mdf.attrib['pdl']})
elif mdf.tag == "lmf_mdf":
# XML elements "lmf_mdf" have 2 XML attributes: one for the name of the marker ("marker"), a second for the variable name ("var")
exec("l = lambda " + mdf.attrib['var'] + ": " + mdf.text)
lmf_mdf.update({mdf.attrib['marker']: l})
elif mdf.tag == "mdf_order":
mdf_order = []
for element in mdf:
mdf_order.append(element.tag)
list1 = []
for level1 in element:
list1.append(level1.tag)
list2 = []
for level2 in level1:
list2.append(level2.tag)
if len(list2) != 0:
list1.append(list2)
if len(list1) != 0:
mdf_order.append(list1)
elif format.tag == "LaTeX":
for param in format:
if param.tag == "partOfSpeech_tex":
# XML elements "partOfSpeech_tex" have 2 or 3 XML attributes: one for the LMF value ("partOfSpeech"), a second for the LaTeX value ("tex"), and an optional one to define language
try:
partOfSpeech_tex.update({(param.attrib['lang'], param.attrib['partOfSpeech']): param.attrib['tex']})
except KeyError:
partOfSpeech_tex.update({param.attrib['partOfSpeech']: param.attrib['tex']})
# Also automatically update range of possible values allowed for LMF part of speech LexicalEntry attribute -->
partOfSpeech_range.add(param.attrib['partOfSpeech'])
elif param.tag == "paradigmLabel_tex":
# XML elements "paradigmLabel_tex" have 2 XML attributes: one for the LMF value ("paradigmLabel"), a second for the LaTeX value ("tex")
paradigmLabel_tex.update({param.attrib['paradigmLabel']: param.attrib['tex']})
# Also automatically update range of possible values allowed for LMF paradigm label Paradigm attribute -->
paradigmLabel_range.add(param.attrib['paradigmLabel'])
else:
raise InputError(module_name + ".py", "XML file '%s' is not well-formatted." % filename)
return lexical_resource
class TestLexicalResourceFunctions(unittest.TestCase):
def setUp(self):
# Instantiate a LexicalResource object
self.lexical_resource = LexicalResource()
def tearDown(self):
# Release instantiated objects
del self.lexical_resource
def test_init(self):
self.assertEqual(self.lexical_resource.dtdVersion, 16)
self.assertIsInstance(self.lexical_resource.global_information,
GlobalInformation)
self.assertListEqual(self.lexical_resource.lexicon, [])
self.assertListEqual(self.lexical_resource.speaker, [])
def test_get_lexicons(self):
# Create lexicons
lexicon1 = Lexicon()
lexicon2 = Lexicon()
# Add lexicons to the lexical resource
self.lexical_resource.lexicon = [lexicon1, lexicon2]
# Test get lexicons
self.assertListEqual(self.lexical_resource.get_lexicons(),
[lexicon1, lexicon2])
# Release Lexicon instances
del self.lexical_resource.lexicon[:]
del lexicon1, lexicon2
def test_add_lexicon(self):
# Create lexicons
lexicon1 = Lexicon()
lexicon2 = Lexicon()
# Test add lexicons to the lexical resource
self.assertEqual(self.lexical_resource.add_lexicon(lexicon1),
self.lexical_resource)
self.assertListEqual(self.lexical_resource.lexicon, [lexicon1])
self.assertEqual(self.lexical_resource.add_lexicon(lexicon2),
self.lexical_resource)
self.assertListEqual(self.lexical_resource.lexicon,
[lexicon1, lexicon2])
# Release Lexicon instances
del self.lexical_resource.lexicon[:]
del lexicon1, lexicon2
def test_remove_lexicon(self):
# Create lexicons
lexicon1 = Lexicon()
lexicon2 = Lexicon()
# Add lexicons to the lexical resource
self.lexical_resource.lexicon = [lexicon1, lexicon2]
# Test remove lexicons
self.assertEqual(self.lexical_resource.remove_lexicon(lexicon1),
self.lexical_resource)
self.assertListEqual(self.lexical_resource.lexicon, [lexicon2])
self.assertEqual(self.lexical_resource.remove_lexicon(lexicon2),
self.lexical_resource)
self.assertListEqual(self.lexical_resource.lexicon, [])
# Release Lexicon instances
del lexicon1, lexicon2
def test_get_lexicon(self):
# Create lexicons
lexicon1 = Lexicon("lexicon1")
lexicon2 = Lexicon("lexicon2")
# Add lexicons to the lexical resource
self.lexical_resource.lexicon = [lexicon1, lexicon2]
# Test get lexicon
self.assertIsNone(
self.lexical_resource.get_lexicon("unknown identifier"))
self.assertEqual(self.lexical_resource.get_lexicon("lexicon2"),
lexicon2)
# Release Lexicon instances
del lexicon1, lexicon2
def test_set_dtdVersion(self):
version = "0"
self.assertEqual(self.lexical_resource.set_dtdVersion(version),
self.lexical_resource)
self.assertEqual(self.lexical_resource.dtdVersion, version)
def test_get_dtdVersion(self):
self.assertIs(self.lexical_resource.get_dtdVersion(),
self.lexical_resource.dtdVersion)
def test_set_language_code(self):
code = "iso"
self.assertEqual(self.lexical_resource.set_language_code(code),
self.lexical_resource)
self.assertEqual(self.lexical_resource.global_information.languageCode,
code)
def test_get_language_code(self):
self.assertIs(self.lexical_resource.get_language_code(),
self.lexical_resource.global_information.languageCode)
def test_set_version(self):
version = "0"
self.assertEqual(self.lexical_resource.set_version(version),
self.lexical_resource)
self.assertEqual(self.lexical_resource.global_information.version,
version)
def test_get_version(self):
self.assertIs(self.lexical_resource.get_version(),
self.lexical_resource.global_information.version)
def test_set_license(self):
license = "free"
self.assertEqual(self.lexical_resource.set_license(license),
self.lexical_resource)
self.assertEqual(self.lexical_resource.global_information.license,
license)
def test_get_license(self):
self.assertIs(self.lexical_resource.get_license(),
self.lexical_resource.global_information.license)
def test_set_character_encoding(self):
coding = "iso"
self.assertEqual(self.lexical_resource.set_character_encoding(coding),
self.lexical_resource)
self.assertEqual(
self.lexical_resource.global_information.characterEncoding, coding)
def test_get_character_encoding(self):
self.assertIs(
self.lexical_resource.get_character_encoding(),
self.lexical_resource.global_information.characterEncoding)
def test_set_date_coding(self):
coding = "iso"
self.assertEqual(self.lexical_resource.set_date_coding(coding),
self.lexical_resource)
self.assertEqual(self.lexical_resource.global_information.dateCoding,
coding)
def test_get_date_coding(self):
self.assertIs(self.lexical_resource.get_date_coding(),
self.lexical_resource.global_information.dateCoding)
def test_set_project_name(self):
name = "project"
self.assertEqual(self.lexical_resource.set_project_name(name),
self.lexical_resource)
self.assertEqual(self.lexical_resource.global_information.projectName,
name)
def test_get_project_name(self):
self.assertIs(self.lexical_resource.get_project_name(),
self.lexical_resource.global_information.projectName)
def test_set_creation_date(self):
date = "2014-10-08"
self.assertEqual(self.lexical_resource.set_creation_date(date),
self.lexical_resource)
self.assertEqual(self.lexical_resource.global_information.creationDate,
date)
def test_get_creation_date(self):
self.assertIs(self.lexical_resource.get_creation_date(),
self.lexical_resource.global_information.creationDate)
def test_set_last_update(self):
date = "2014-10-10"
self.assertEqual(self.lexical_resource.set_last_update(date),
self.lexical_resource)
self.assertEqual(self.lexical_resource.global_information.lastUpdate,
date)
def test_get_last_update(self):
self.assertIs(self.lexical_resource.get_last_update(),
self.lexical_resource.global_information.lastUpdate)
def test_set_author(self):
author = "My Name"
self.assertEqual(self.lexical_resource.set_author(author),
self.lexical_resource)
self.assertEqual(self.lexical_resource.global_information.author,
author)
def test_get_author(self):
self.assertIs(self.lexical_resource.get_author(),
self.lexical_resource.global_information.author)
def test_set_description(self):
descr = "This is a short description of this lexical resource."
self.assertEqual(self.lexical_resource.set_description(descr),
self.lexical_resource)
self.assertEqual(self.lexical_resource.global_information.description,
descr)
def test_get_description(self):
self.assertIs(self.lexical_resource.get_description(),
self.lexical_resource.global_information.description)
def test_get_bibliographic_citation(self):
self.assertIs(
self.lexical_resource.get_bibliographic_citation(),
self.lexical_resource.global_information.bibliographicCitation)