def write_result(element, filename, encoding=ENCODING):
"""! @brief Write an XML element into a pretty XML output file.
@param element An XML element.
@param filename The name of the XML file to write with full path, for instance 'output.xml'.
@param encoding Encoding mode. Default value is 'utf-8'.
"""
unicode_str = prettify(element, encoding=encoding)
output_file = open_write(filename, encoding=encoding)
output_file.write(unicode_str.decode(encoding))
output_file.close()
def write_result(element, filename, encoding=ENCODING):
"""! @brief Write an XML element into a pretty XML output file.
@param element An XML element.
@param filename The name of the XML file to write with full path, for instance 'output.xml'.
@param encoding Encoding mode. Default value is 'utf-8'.
"""
unicode_str = prettify(element, encoding=encoding)
output_file = open_write(filename, encoding=encoding)
output_file.write(unicode_str.decode(encoding))
output_file.close()
def test_open_write(self):
import sys, os
utest_path = sys.path[0] + '/'
test_filename = utest_path + "test_file"
test_string = "Test string."
# Test open and write file
test_file = open_write(test_filename)
test_file.write(test_string)
test_file.close()
# Read file
test_file = open_file(test_filename, 'r')
self.assertEqual(test_file.readline(), test_string)
test_file.close()
# Remove test file
os.remove(test_filename)
def test_open_write(self):
import sys, os
utest_path = sys.path[0] + '/'
test_filename = utest_path + "test_file"
test_string = "Test string."
# Test open and write file
test_file = open_write(test_filename)
test_file.write(test_string)
test_file.close()
# Read file
test_file = open_file(test_filename, 'r')
self.assertEqual(test_file.readline(), test_string)
test_file.close()
# Remove test file
os.remove(test_filename)
def mdf_write(object, filename, lmf2mdf=lmf_mdf, order=mdf_order):
"""! @brief Write an MDF file.
@param object The LMF instance to convert into MDF output format.
@param filename The name of the MDF file to write with full path, for instance 'user/output.txt'.
@param lmf2mdf A Python dictionary describing the mapping between LMF representation and MDF markers. Default value is 'lmf_mdf' dictionary defined in 'pylmflib/config/mdf.py'. Please refer to it as an example.
@param order A Python list defining the order in which MDF markers must be written, for instance ["lx", "ps"]. Default value is 'mdf_order' list defined in 'pylmflib/config/mdf.py'.
"""
mdf_file = open_write(filename)
# For each MDF marker, get the corresponding LMF value
if object.__class__.__name__ == "Lexicon":
for lexical_entry in object.get_lexical_entries():
for marker in order:
if type(marker) is list:
# Parse group of markers
parse_list(mdf_file, lmf2mdf, marker, lexical_entry)
else:
value = lmf2mdf[marker](lexical_entry)
write_line(mdf_file, marker, value)
# Separate lexical entries from each others with a blank line
mdf_file.write(EOL)
else:
raise OutputError(object, "Object to write must be a Lexicon.")
mdf_file.close()
def mdf_write(object, filename, lmf2mdf=lmf_mdf, order=mdf_order):
"""! @brief Write an MDF file.
@param object The LMF instance to convert into MDF output format.
@param filename The name of the MDF file to write with full path, for instance 'user/output.txt'.
@param lmf2mdf A Python dictionary describing the mapping between LMF representation and MDF markers. Default value is 'lmf_mdf' dictionary defined in 'pylmflib/config/mdf.py'. Please refer to it as an example.
@param order A Python list defining the order in which MDF markers must be written, for instance ["lx", "ps"]. Default value is 'mdf_order' list defined in 'pylmflib/config/mdf.py'.
"""
mdf_file = open_write(filename)
# For each MDF marker, get the corresponding LMF value
if object.__class__.__name__ == "Lexicon":
for lexical_entry in object.get_lexical_entries():
for marker in order:
if type(marker) is list:
# Parse group of markers
parse_list(mdf_file, lmf2mdf, marker, lexical_entry)
else:
value = lmf2mdf[marker](lexical_entry)
write_line(mdf_file, marker, value)
# Separate lexical entries from each others with a blank line
mdf_file.write(EOL)
else:
raise OutputError(object, "Object to write must be a Lexicon.")
mdf_file.close()
def tex_write(object, filename, preamble=None, introduction=None, lmf2tex=lmf_to_tex, font=None, items=lambda lexical_entry: lexical_entry.get_lexeme(), sort_order=None, paradigms=[], tables=[], title=None, tex_language=None):
"""! @brief Write a LaTeX file.
Note that the lexicon must already be ordered at this point. Here, parameters 'items' and 'sort_order' are only used to define chapters.
@param object The LMF instance to convert into LaTeX output format.
@param filename The name of the LaTeX file to write with full path, for instance 'user/output.tex'.
@param preamble The name of the LaTeX file with full path containing the LaTeX header of the document, for instance 'user/config/japhug.tex'. Default value is None.
@param introduction The name of the LaTeX file with full path containing the LaTeX introduction of the document, for instance 'user/config/introduction.tex'. Default value is None.
@param lmf2tex A function giving the mapping from LMF representation information that must be written to LaTeX commands, in a defined order. Default value is 'lmf_to_tex' function defined in 'pylmflib/config/tex.py'. Please refer to it as an example.
@param font A Python dictionary giving the vernacular, national, regional fonts to apply to a text in LaTeX format.
@param items Lambda function giving the item to sort. Default value is 'lambda lexical_entry: lexical_entry.get_lexeme()', which means that the items to sort are lexemes.
@param sort_order Default value is 'None', which means that the LaTeX output is alphabetically ordered.
@param paradigms A Python list of LaTeX filenames with full path containing the paradigms in LaTeX format. Default value is an empty list.
@param tables The name of the LaTeX file with full path containing some notes to add at the end of the LaTeX document, for instance 'user/config/conclusion.tex'. Default value is None.
@param title A Python string containing the title of the LaTeX document. Default value is None.
@param tex_language A Python string giving the default language to set in LaTeX.
"""
import string, os
# Define font
if font is None:
font = config.xml.font
tex_file = open_write(filename)
# Add file header if any
tex_file.write(file_read(preamble))
# Continue the header if needed
if title is not None:
tex_file.write("\\title{" + title + "}" + EOL)
if tex_language is not None:
tex_file.write("\setdefaultlanguage{" + tex_language + "}" + EOL)
# Insert LaTeX commands to create a document
tex_file.write(EOL + "\\begin{document}" + EOL)
tex_file.write("\\maketitle" + EOL)
tex_file.write("\\newpage" + EOL)
# Add introduction if any
if introduction is not None:
tex_file.write("\\markboth{INTRODUCTION}{}" + EOL * 2)
tex_file.write(file_read(introduction))
# Add command for small caps
tex_file.write(EOL + "\\def\\mytextsc{\\bgroup\\obeyspaces\\mytextscaux}" + EOL)
tex_file.write("\\def\\mytextscaux#1{\\mytextscauxii #1\\relax\\relax\\egroup}" + EOL)
tex_file.write("\\def\\mytextscauxii#1{%" + EOL)
tex_file.write("\\ifx\\relax#1\\else \\ifcat#1\\@sptoken{} \\expandafter\\expandafter\\expandafter\\mytextscauxii\\else" + EOL)
tex_file.write("\\ifnum`#1=\\uccode`#1 {\\normalsize #1}\\else {\\footnotesize \\uppercase{#1}}\\fi \\expandafter\\expandafter\\expandafter\\mytextscauxii\\expandafter\\fi\\fi}" + EOL * 2)
# Configure space indent
tex_file.write("\\setlength\\parindent{0cm}" + EOL)
# Insert data path configuration
# Unix-style paths
audio_path = config.xml.audio_path
graphic_path = os.path.abspath('.')
if os.name != 'posix':
# Windows-style paths
audio_path = audio_path.replace("\\", "/")
graphic_path = graphic_path.replace("\\", "/")
tex_file.write(EOL + "\\addmediapath{" + audio_path.rstrip("/") + "}" + EOL)
tex_file.write("\\addmediapath{" + audio_path + "mp3}" + EOL)
tex_file.write("\\addmediapath{" + audio_path + "wav}" + EOL)
tex_file.write("\\graphicspath{{" + graphic_path + "/pylmflib/output/img/}}" + EOL * 2)
# Configure 2 columns
tex_file.write("\\newpage" + EOL)
tex_file.write("\\begin{multicols}{2}" + EOL * 2)
if sort_order is None:
# Lowercase and uppercase letters must have the same rank
sort_order = dict([(c, ord(c)) for c in string.lowercase])
up = dict([(c, ord(c) + 32) for c in string.uppercase])
sort_order.update(up)
sort_order.update({'':0, ' ':0})
# For each element to write, get the corresponding LMF value
if object.__class__.__name__ == "LexicalResource":
for lexicon in object.get_lexicons():
previous_character = ''
current_character = ''
# Lexicon is already ordered
for lexical_entry in lexicon.get_lexical_entries():
# Consider only main entries (subentries and components will be written as parts of the main entry)
if lexical_entry.find_related_forms("main entry") == [] and lexical_entry.get_independentWord() is not False:
# Check if current element is a lexeme starting with a different character than previous lexeme
try:
current_character = items(lexical_entry)[0]
if sort_order[items(lexical_entry)[0:1]]:
current_character = items(lexical_entry)[0:1]
if sort_order[items(lexical_entry)[0:2]]:
current_character = items(lexical_entry)[0:2]
except IndexError:
pass
except KeyError:
pass
except TypeError:
pass
try:
if ( (type(sort_order) is not type(dict())) and ((previous_character == '') or (sort_order(current_character) != sort_order(previous_character))) ) \
or ( (type(sort_order) is type(dict())) and (int(sort_order[current_character]) != int(sort_order[previous_character])) ):
# Do not consider special characters
previous_character = current_character
tex_file.write("\\newpage" + EOL)
title = ''
if type(sort_order) is not type(dict()):
title += ' ' + font[NATIONAL](current_character)
else:
for key,value in sorted(sort_order.items(), key=lambda x: x[1]):
if int(value) == int(sort_order[current_character]):
title += ' ' + font[VERNACULAR](key)
tex_file.write("\\section*{\\centering-" + handle_reserved(title) + " -}" + EOL)
#tex_file.write("\\pdfbookmark[1]{" + title + " }{" + title + " }" + EOL)
tex_file.write(lmf2tex(lexical_entry, font))
if len(paradigms) != 0:
tex_file.write(insert_references(lexical_entry))
tex_file.write("\\lhead{\\firstmark}" + EOL)
tex_file.write("\\rhead{\\botmark}" + EOL)
# Separate lexical entries from each others with a blank line
tex_file.write(EOL)
# Handle subentries
for related_form in lexical_entry.get_related_forms("subentry"):
if related_form.get_lexical_entry() is not None:
tex_file.write(lmf2tex(related_form.get_lexical_entry(), font))
if len(paradigms) != 0:
tex_file.write(insert_references(related_form.get_lexical_entry()))
# Separate sub-entries from each others with a blank line
tex_file.write(EOL)
except KeyError:
print Warning("Cannot sort item %s" % items(lexical_entry).encode(ENCODING))
except IndexError:
# Item is an empty string
pass
else:
raise OutputError(object, "Object to write must be a Lexical Resource.")
# Insert LaTeX commands to finish the document properly
tex_file.write("\end{multicols}" + EOL)
# Insert paradigms if any
for filename in paradigms:
tex_file.write(EOL)
tex_file.write("\\newpage" + EOL)
tex_file.write("\markboth{paradigms}{}" + EOL)
tex_file.write(file_read(filename))
tex_file.write(EOL)
# Insert other tables if any
for filename in tables:
tex_file.write(EOL)
tex_file.write("\\newpage" + EOL)
tex_file.write(file_read(filename))
tex_file.write(EOL)
tex_file.write("\end{document}" + EOL)
tex_file.close()
def tex_write(object,
filename,
preamble=None,
introduction=None,
lmf2tex=lmf_to_tex,
font=None,
items=lambda lexical_entry: lexical_entry.get_lexeme(),
sort_order=None,
paradigms=[],
tables=[],
title=None,
tex_language=None):
"""! @brief Write a LaTeX file.
Note that the lexicon must already be ordered at this point. Here, parameters 'items' and 'sort_order' are only used to define chapters.
@param object The LMF instance to convert into LaTeX output format.
@param filename The name of the LaTeX file to write with full path, for instance 'user/output.tex'.
@param preamble The name of the LaTeX file with full path containing the LaTeX header of the document, for instance 'user/config/japhug.tex'. Default value is None.
@param introduction The name of the LaTeX file with full path containing the LaTeX introduction of the document, for instance 'user/config/introduction.tex'. Default value is None.
@param lmf2tex A function giving the mapping from LMF representation information that must be written to LaTeX commands, in a defined order. Default value is 'lmf_to_tex' function defined in 'pylmflib/config/tex.py'. Please refer to it as an example.
@param font A Python dictionary giving the vernacular, national, regional fonts to apply to a text in LaTeX format.
@param items Lambda function giving the item to sort. Default value is 'lambda lexical_entry: lexical_entry.get_lexeme()', which means that the items to sort are lexemes.
@param sort_order Default value is 'None', which means that the LaTeX output is alphabetically ordered.
@param paradigms A Python list of LaTeX filenames with full path containing the paradigms in LaTeX format. Default value is an empty list.
@param tables The name of the LaTeX file with full path containing some notes to add at the end of the LaTeX document, for instance 'user/config/conclusion.tex'. Default value is None.
@param title A Python string containing the title of the LaTeX document. Default value is None.
@param tex_language A Python string giving the default language to set in LaTeX.
"""
import string, os
# Define font
if font is None:
font = config.xml.font
tex_file = open_write(filename)
# Add file header if any
tex_file.write(file_read(preamble))
# Continue the header if needed
if title is not None:
tex_file.write("\\title{" + unicode(title, "utf-8") + "}" + EOL)
if tex_language is not None:
tex_file.write("\setdefaultlanguage{" + tex_language + "}" + EOL)
# Insert LaTeX commands to create a document
tex_file.write(EOL + "\\begin{document}" + EOL)
tex_file.write("\\maketitle" + EOL)
tex_file.write("\\newpage" + EOL)
# Add introduction if any
if introduction is not None:
tex_file.write("\\markboth{INTRODUCTION}{}" + EOL * 2)
tex_file.write(file_read(introduction))
# Add command for small caps
tex_file.write(EOL + "\\def\\mytextsc{\\bgroup\\obeyspaces\\mytextscaux}" +
EOL)
tex_file.write(
"\\def\\mytextscaux#1{\\mytextscauxii #1\\relax\\relax\\egroup}" + EOL)
tex_file.write("\\def\\mytextscauxii#1{%" + EOL)
tex_file.write(
"\\ifx\\relax#1\\else \\ifcat#1\\@sptoken{} \\expandafter\\expandafter\\expandafter\\mytextscauxii\\else"
+ EOL)
tex_file.write(
"\\ifnum`#1=\\uccode`#1 {\\normalsize #1}\\else {\\footnotesize \\uppercase{#1}}\\fi \\expandafter\\expandafter\\expandafter\\mytextscauxii\\expandafter\\fi\\fi}"
+ EOL * 2)
# Configure space indent
tex_file.write("\\setlength\\parindent{0cm}" + EOL)
# Insert data path configuration
# Unix-style paths
audio_path = config.xml.audio_path
graphic_path = os.path.abspath('.')
if os.name != 'posix':
# Windows-style paths
audio_path = audio_path.replace("\\", "/")
graphic_path = graphic_path.replace("\\", "/")
tex_file.write(EOL + "\\addmediapath{" + audio_path.rstrip("/") + "}" +
EOL)
tex_file.write("\\addmediapath{" + audio_path + "mp3}" + EOL)
tex_file.write("\\addmediapath{" + audio_path + "wav}" + EOL)
tex_file.write("\\graphicspath{{" + graphic_path +
"/pylmflib/output/img/}}" + EOL * 2)
# Configure 2 columns
tex_file.write("\\newpage" + EOL)
tex_file.write("\\begin{multicols}{2}" + EOL * 2)
if sort_order is None:
# Lowercase and uppercase letters must have the same rank
sort_order = dict([(c, ord(c)) for c in string.lowercase])
up = dict([(c, ord(c) + 32) for c in string.uppercase])
sort_order.update(up)
sort_order.update({'': 0, ' ': 0})
# For each element to write, get the corresponding LMF value
if object.__class__.__name__ == "LexicalResource":
for lexicon in object.get_lexicons():
previous_character = ''
current_character = ''
# Lexicon is already ordered
for lexical_entry in lexicon.get_lexical_entries():
# Consider only main entries (subentries and components will be written as parts of the main entry)
if lexical_entry.find_related_forms(
"main entry"
) == [] and lexical_entry.get_independentWord() is not False:
# Check if current element is a lexeme starting with a different character than previous lexeme
try:
current_character = items(lexical_entry)[0]
if sort_order[items(lexical_entry)[0:1]]:
current_character = items(lexical_entry)[0:1]
if sort_order[items(lexical_entry)[0:2]]:
current_character = items(lexical_entry)[0:2]
except IndexError:
pass
except KeyError:
pass
except TypeError:
pass
try:
if ( (type(sort_order) is not type(dict())) and ((previous_character == '') or (sort_order(current_character) != sort_order(previous_character))) ) \
or ( (type(sort_order) is type(dict())) and (int(sort_order[current_character]) != int(sort_order[previous_character])) ):
# Do not consider special characters
previous_character = current_character
tex_file.write("\\newpage" + EOL)
title = ''
if type(sort_order) is not type(dict()):
title += ' ' + font[NATIONAL](
current_character)
else:
for key, value in sorted(sort_order.items(),
key=lambda x: x[1]):
if int(value) == int(
sort_order[current_character]):
title += ' ' + font[VERNACULAR](key)
tex_file.write("\\section*{\\centering-" +
handle_reserved(title) + " -}" +
EOL)
#tex_file.write("\\pdfbookmark[1]{" + title + " }{" + title + " }" + EOL)
tex_file.write(lmf2tex(lexical_entry, font))
if len(paradigms) != 0:
tex_file.write(insert_references(lexical_entry))
# tex_file.write("\\lhead{\\firstmark}" + EOL)
# tex_file.write("\\rhead{\\botmark}" + EOL)
# Separate lexical entries from each others with a blank line
tex_file.write(EOL)
# Handle subentries
for related_form in lexical_entry.get_related_forms(
"subentry"):
if related_form.get_lexical_entry() is not None:
tex_file.write(
lmf2tex(related_form.get_lexical_entry(),
font))
if len(paradigms) != 0:
tex_file.write(
insert_references(
related_form.get_lexical_entry()))
# Separate sub-entries from each others with a blank line
tex_file.write(EOL)
except KeyError:
print Warning("Cannot sort item %s" %
items(lexical_entry).encode(ENCODING))
except IndexError:
# Item is an empty string
pass
else:
raise OutputError(object,
"Object to write must be a Lexical Resource.")
# Insert LaTeX commands to finish the document properly
tex_file.write("\end{multicols}" + EOL)
# Insert paradigms if any
for filename in paradigms:
tex_file.write(EOL)
tex_file.write("\\newpage" + EOL)
tex_file.write("\markboth{paradigms}{}" + EOL)
tex_file.write(file_read(filename))
tex_file.write(EOL)
# Insert other tables if any
for filename in tables:
tex_file.write(EOL)
tex_file.write("\\newpage" + EOL)
tex_file.write(file_read(filename))
tex_file.write(EOL)
tex_file.write("\end{document}" + EOL)
tex_file.close()
