def lmf2tex(lexical_entry, font):
import output.tex as tex
tex_entry = ""
# lexeme, id and phonetic variants
tex_entry += tex.format_lexeme(lexical_entry, font)
# sound
tex_entry += tex.format_audio(lexical_entry, font)
# part of speech
tex_entry += tex.format_part_of_speech(lexical_entry, font)
# grammatical notes
tex_entry += tex.format_notes(lexical_entry, font)
# Order by sense number
senses = lexical_entry.get_senses()
senses.sort(key=lambda sense: sense.get_senseNumber(integer=True))
for sense in senses:
if sense.get_senseNumber() is not None:
tex_entry += sense.get_senseNumber() + ") "
# definition/gloss and translation
tex_entry += tex.format_definitions(sense,
font,
languages=[
config.xml.vernacular,
config.xml.French,
config.xml.national
])
# example
tex_entry += tex.format_examples(sense, font)
# usage note
tex_entry += tex.format_usage_notes(sense, font)
# encyclopedic information
tex_entry += tex.format_encyclopedic_informations(sense, font)
# restriction
tex_entry += tex.format_restrictions(sense, font)
# synonym, antonym, morphology, related form
tex_entry += tex.format_related_forms(lexical_entry, font)
# borrowed word
tex_entry += tex.format_borrowed_word(lexical_entry, font)
# etymology
tex_entry += tex.format_etymology(lexical_entry, font)
# paradigms
tex_entry += tex.format_paradigms(lexical_entry, font)
tex_entry += tex.format_paradigms(lexical_entry, font)
# semantic domain
tex_entry += tex.format_semantic_domains(lexical_entry, font)
# source
tex_entry += tex.format_source(lexical_entry, font)
# status
tex_entry += tex.format_status(lexical_entry, font)
# date
tex_entry += tex.format_date(lexical_entry, font)
# Handle reserved characters and fonts
tex_entry = tex.handle_reserved(tex_entry)
tex_entry = tex.handle_quotes(tex_entry)
tex_entry = tex.handle_fv(tex_entry, font)
tex_entry = tex.handle_fn(tex_entry, font)
# Special formatting
tex_entry = tex.handle_pinyin(tex_entry)
tex_entry = tex.handle_caps(tex_entry)
return tex_entry + EOL
def lmf2tex(lexical_entry, font):
tex_entry = ""
if lmf2tex.is_first_entry:
tex_entry += "\\setlength{\\parskip}{-0.5cm}" + EOL
lmf2tex.is_first_entry = False
# lexeme, id and phonetic variants
tex_entry += format_lexeme(lexical_entry, font)
# sound
tex_entry += tex.format_audio(lexical_entry, font)
# part of speech
tex_entry += tex.format_part_of_speech(lexical_entry, font)
# grammatical notes
tex_entry += format_notes(lexical_entry, font)
# Order by sense number
senses = lexical_entry.get_senses()
senses.sort(key=lambda sense: sense.get_senseNumber(integer=True))
for sense in senses:
if sense.get_senseNumber() is not None:
# In LaTeX, "\ding{202}" represents '➊' character, "\ding{203}" '➋' character, etc.
code = 201 + int(sense.get_senseNumber())
tex_entry += "\ding{" + str(code) + "} "
# paradigms
tex_entry += format_paradigms(sense, font)
# definition/gloss and translation
tex_entry += format_definitions(sense, font, languages=[config.xml.vernacular, config.xml.French, config.xml.national])
# example
tex_entry += format_examples(sense, font)
# usage note
tex_entry += format_usage_notes(sense, font)
# encyclopedic information
tex_entry += format_encyclopedic_informations(sense, font)
# restriction
tex_entry += tex.format_restrictions(sense, font)
# synonym, antonym, morphology, related form
tex_entry += tex.format_related_forms(lexical_entry, font, language=config.xml.French)
# borrowed word
tex_entry += tex.format_borrowed_word(lexical_entry, font)
# etymology
tex_entry += tex.format_etymology(lexical_entry, font)
# paradigms
tex_entry += tex.format_paradigms(lexical_entry, font)
# semantic domain
tex_entry += tex.format_semantic_domains(lexical_entry, font)
# source
tex_entry += tex.format_source(lexical_entry, font)
# status
tex_entry += tex.format_status(lexical_entry, font)
# date
tex_entry += tex.format_date(lexical_entry, font)
# Special formatting
tex_entry = tex.handle_pinyin(tex_entry)
tex_entry = tex.handle_caps(tex_entry)
# Handle reserved characters and fonts
tex_entry = tex.handle_quotes(tex_entry)
tex_entry = tex.handle_reserved(tex_entry)
tex_entry = tex.handle_fv(tex_entry, font)
tex_entry = tex.handle_fn(tex_entry, font)
return tex_entry + EOL
def format_lexeme(lexical_entry, font):
result = ""
if len(lexical_entry.get_components()) != 0:
lexeme = ""
for component in lexical_entry.get_components():
lexeme += component.get_lexeme() + ","
# Remove last punctuation
lexeme = lexeme.rstrip(",")
# Apply font
# lexeme = font[VERNACULAR](lexeme)
else:
if lexical_entry.is_subentry():
lexeme = font[VERNACULAR](lexical_entry.get_lexeme())
else:
lexeme = ""
if lexical_entry.is_subentry():
# result += "\\subparagraph{\\dollar\\blacksquare\\dollar "
# result += "\\begin{adjustwidth}{1em}{} "
result += "\\begin{subentry}{"
# print "totototototototototototototo"
else:
if len(lexical_entry.get_components()) != 0:
result += "\\begin{entry}{"
else:
result += "\\begin{entry}{" + lexical_entry.get_lexeme() # + "}"
# result += "\\vspace{0.5cm} \\paragraph{\\hspace{-0.5cm} "
if lexical_entry.get_homonymNumber() is not None:
# Add homonym number to lexeme
lexeme += " \\textsubscript{" + str(
lexical_entry.get_homonymNumber()) + "}"
if lexical_entry.get_contextual_variations() is not None and len(
lexical_entry.get_contextual_variations()) != 0:
# Format contextual variations
for var in lexical_entry.get_contextual_variations():
result += " " + font[VERNACULAR](var)
result += " (de : " + lexeme + ")."
else:
# Format lexeme
result += lexeme
for form in lexical_entry.get_variant_forms(type="phonetics"):
result += " / " + font[VERNACULAR](form)
result += "} \\hypertarget{" + tex.format_uid(lexical_entry,
font) + "}{}" + EOL
if not lexical_entry.is_subentry():
# result += "\markboth{" + lexeme + "}{}" + EOL
pass
if len(lexical_entry.get_components()) != 0:
# Add components part of speech
result += "pc("
for component in lexical_entry.get_components():
if component.get_lexical_entry() is not None:
result += tex.format_part_of_speech(
component.get_lexical_entry(), font)
result = result.rstrip(". ") + ", "
# Handle last punctuation
result = result.rstrip(", ")
result += ("). ")
return result
def lmf2tex(lexical_entry, font):
import output.tex as tex
tex_entry = ""
# lexeme, id and phonetic variants
tex_entry += tex.format_lexeme(lexical_entry, font)
# sound
tex_entry += tex.format_audio(lexical_entry, font)
# part of speech
tex_entry += tex.format_part_of_speech(lexical_entry, font)
# grammatical notes
tex_entry += tex.format_notes(lexical_entry, font)
# Order by sense number
senses = lexical_entry.get_senses()
senses.sort(key=lambda sense: sense.get_senseNumber(integer=True))
for sense in senses:
if sense.get_senseNumber() is not None:
tex_entry += sense.get_senseNumber() + ") "
# definition/gloss and translation
tex_entry += tex.format_definitions(sense, font, languages=[config.xml.vernacular, config.xml.French, config.xml.national])
# example
tex_entry += tex.format_examples(sense, font)
# usage note
tex_entry += tex.format_usage_notes(sense, font)
# encyclopedic information
tex_entry += tex.format_encyclopedic_informations(sense, font)
# restriction
tex_entry += tex.format_restrictions(sense, font)
# synonym, antonym, morphology, related form
tex_entry += tex.format_related_forms(lexical_entry, font)
# borrowed word
tex_entry += tex.format_borrowed_word(lexical_entry, font)
# etymology
tex_entry += tex.format_etymology(lexical_entry, font)
# paradigms
tex_entry += tex.format_paradigms(lexical_entry, font)
tex_entry += tex.format_paradigms(lexical_entry, font)
# semantic domain
tex_entry += tex.format_semantic_domains(lexical_entry, font)
# source
tex_entry += tex.format_source(lexical_entry, font)
# status
tex_entry += tex.format_status(lexical_entry, font)
# date
tex_entry += tex.format_date(lexical_entry, font)
# Handle reserved characters and fonts
tex_entry = tex.handle_reserved(tex_entry)
tex_entry = tex.handle_quotes(tex_entry)
tex_entry = tex.handle_fv(tex_entry, font)
tex_entry = tex.handle_fn(tex_entry, font)
# Special formatting
tex_entry = tex.handle_pinyin(tex_entry)
tex_entry = tex.handle_caps(tex_entry)
return tex_entry + EOL
def format_lexeme(lexical_entry, font):
result = ""
if len(lexical_entry.get_components()) != 0:
lexeme = ""
for component in lexical_entry.get_components():
lexeme += component.get_lexeme() + ","
# Remove last punctuation
lexeme = lexeme.rstrip(",")
# Apply font
lexeme = font[VERNACULAR](lexeme)
else:
lexeme = font[VERNACULAR](lexical_entry.get_lexeme())
if lexical_entry.is_subentry():
result += "\\subparagraph{\\dollar\\blacksquare\\dollar "
else:
result += "\\vspace{0.5cm} \\paragraph{\\hspace{-0.5cm} "
if lexical_entry.get_homonymNumber() is not None:
# Add homonym number to lexeme
lexeme += " \\textsubscript{" + str(lexical_entry.get_homonymNumber()) + "}"
if lexical_entry.get_contextual_variations() is not None and len(lexical_entry.get_contextual_variations()) != 0:
# Format contextual variations
for var in lexical_entry.get_contextual_variations():
result += " " + font[VERNACULAR](var)
result += " (de : " + lexeme + ")."
else:
# Format lexeme
result += lexeme
for form in lexical_entry.get_variant_forms(type = "phonetics"):
result += " / " + font[VERNACULAR](form)
result += "} \\hypertarget{" + tex.format_uid(lexical_entry, font) + "}{}" + EOL
if not lexical_entry.is_subentry():
result += "\markboth{" + lexeme + "}{}" + EOL
if len(lexical_entry.get_components()) != 0:
# Add components part of speech
result += "pc("
for component in lexical_entry.get_components():
if component.get_lexical_entry() is not None:
result += tex.format_part_of_speech(component.get_lexical_entry(), font)
result = result.rstrip(". ") + ", "
# Handle last punctuation
result = result.rstrip(", ")
result += ("). ")
return result
def lmf_to_tex(lexical_entry, font=None, partOfSpeech_mapping=partOfSpeech_tex, languages=[VERNACULAR, ENGLISH, NATIONAL, REGIONAL]):
"""! @brief Function to convert LMF lexical entry information to be written into LaTeX commands.
@param lexical_entry The Lexical Entry LMF instance to display.
@param font A Python dictionary describing fonts to use for different languages.
@param partOfSpeech_mapping A Python dictionary giving abbreviations for LMF part of speech values.
@param languages A list of languages to consider for LaTeX layout (all by default).
@return A string representing the lexical entry in LaTeX format.
"""
import output.tex as tex
# Define font
if font is None:
font = config.xml.font
tex_entry = ""
# lexeme and id
tex_entry += tex.format_lexeme(lexical_entry, font)
# sound
tex_entry += tex.format_audio(lexical_entry, font)
# part of speech
tex_entry += tex.format_part_of_speech(lexical_entry, font, mapping=partOfSpeech_mapping)
# Order by sense number
senses = lexical_entry.get_senses()
senses.sort(key=lambda sense: sense.get_senseNumber(integer=True))
for sense in senses:
if sense.get_senseNumber() is not None:
tex_entry += sense.get_senseNumber() + ") "
# definition/gloss and translation
tex_entry += tex.format_definitions(sense, font, languages)
# TODO
tex_entry += tex.format_lt(sense, font)
tex_entry += tex.format_sc(sense, font)
tex_entry += tex.format_rf(sense, font)
# example
tex_entry += tex.format_examples(sense, font)
# usage note
tex_entry += tex.format_usage_notes(sense, font)
# encyclopedic information
tex_entry += tex.format_encyclopedic_informations(sense, font)
# restriction
tex_entry += tex.format_restrictions(sense, font)
# TODO
tex_entry += tex.format_lexical_functions(lexical_entry, font)
# synonym, antonym, morphology, related form
tex_entry += tex.format_related_forms(lexical_entry, font)
# variant form
tex_entry += tex.format_variant_forms(lexical_entry, font)
# borrowed word
tex_entry += tex.format_borrowed_word(lexical_entry, font)
# etymology
tex_entry += tex.format_etymology(lexical_entry, font)
# paradigms
tex_entry += tex.format_paradigms(lexical_entry, font)
# TODO
tex_entry += tex.format_table(lexical_entry, font)
# semantic domain
tex_entry += tex.format_semantic_domains(lexical_entry, font)
# bibliography
tex_entry += tex.format_bibliography(lexical_entry, font)
# TODO
tex_entry += tex.format_picture(lexical_entry, font)
# notes
tex_entry += tex.format_notes(lexical_entry, font)
# source
tex_entry += tex.format_source(lexical_entry, font)
# status
tex_entry += tex.format_status(lexical_entry, font)
# date
tex_entry += tex.format_date(lexical_entry, font)
# Handle reserved characters and fonts
tex_entry = tex.handle_reserved(tex_entry)
tex_entry = tex.handle_quotes(tex_entry)
tex_entry = tex.handle_fv(tex_entry, font)
tex_entry = tex.handle_fn(tex_entry, font)
# Special formatting
tex_entry = tex.handle_pinyin(tex_entry)
tex_entry = tex.handle_caps(tex_entry)
return tex_entry + EOL
def lmf2tex(lexical_entry, font):
import output.tex as tex
tex_entry = ""
if lmf2tex.is_first_entry:
tex_entry += "\\setlength{\\parskip}{-0.5cm}" + EOL
lmf2tex.is_first_entry = False
# lexeme and id
tex_entry += format_lexeme(lexical_entry, config.xml.font)
# TODO: phonetic variants ? or variant form ?
# sound
tex_entry += tex.format_audio(lexical_entry, config.xml.font)
# part of speech
tex_entry += tex.format_part_of_speech(lexical_entry, config.xml.font)
# grammatical notes
tex_entry += format_notes(lexical_entry, config.xml.font)
# Order by sense number
senses = lexical_entry.get_senses()
senses.sort(key=lambda sense: sense.get_senseNumber(integer=True))
for sense in senses:
if sense.get_senseNumber() is not None:
# In LaTeX, "\ding{202}" represents '➊' character, "\ding{203}" '➋' character, etc.
code = 201 + int(sense.get_senseNumber())
tex_entry += "\ding{" + str(code) + "} "
# definition/gloss and translation
tex_entry += tex.format_definitions(sense,
config.xml.font,
languages=[
config.xml.vernacular,
config.xml.English,
config.xml.national
])
# example
tex_entry += format_examples_compact(sense, config.xml.font)
# usage note
tex_entry += tex.format_usage_notes(sense, config.xml.font)
# encyclopedic information
tex_entry += tex.format_encyclopedic_informations(
sense, config.xml.font)
# restriction
tex_entry += tex.format_restrictions(sense, config.xml.font)
# synonym, antonym, morphology, related form
tex_entry += tex.format_related_forms(lexical_entry, config.xml.font)
# TODO: variant form?
tex_entry += tex.format_variant_forms(lexical_entry, config.xml.font)
# borrowed word
tex_entry += tex.format_borrowed_word(lexical_entry, config.xml.font)
# etymology
tex_entry += tex.format_etymology(lexical_entry, config.xml.font)
# paradigms
tex_entry += format_paradigms(lexical_entry, config.xml.font)
# semantic domain
tex_entry += tex.format_semantic_domains(lexical_entry, config.xml.font)
# TODO? bibliography
tex_entry += tex.format_bibliography(lexical_entry, config.xml.font)
# source
tex_entry += tex.format_source(lexical_entry, config.xml.font)
# status
tex_entry += tex.format_status(lexical_entry, config.xml.font)
# date
tex_entry += tex.format_date(lexical_entry, config.xml.font)
# Handle reserved characters and fonts
tex_entry = handle_reserved(tex_entry)
tex_entry = tex.handle_quotes(tex_entry)
tex_entry = tex.handle_fv(tex_entry, config.xml.font)
tex_entry = tex.handle_fn(tex_entry, config.xml.font)
# Special formatting
tex_entry = tex.handle_pinyin(tex_entry)
tex_entry = tex.handle_caps(tex_entry)
return tex_entry + EOL
def lmf_to_tex(lexical_entry,
font=None,
partOfSpeech_mapping=partOfSpeech_tex,
languages=[VERNACULAR, ENGLISH, NATIONAL, REGIONAL]):
"""! @brief Function to convert LMF lexical entry information to be written into LaTeX commands.
@param lexical_entry The Lexical Entry LMF instance to display.
@param font A Python dictionary describing fonts to use for different languages.
@param partOfSpeech_mapping A Python dictionary giving abbreviations for LMF part of speech values.
@param languages A list of languages to consider for LaTeX layout (all by default).
@return A string representing the lexical entry in LaTeX format.
"""
import output.tex as tex
# Define font
if font is None:
font = config.xml.font
tex_entry = ""
# lexeme and id
tex_entry += tex.format_lexeme(lexical_entry, font)
# sound
tex_entry += tex.format_audio(lexical_entry, font)
# part of speech
tex_entry += tex.format_part_of_speech(lexical_entry,
font,
mapping=partOfSpeech_mapping)
# Order by sense number
senses = lexical_entry.get_senses()
senses.sort(key=lambda sense: sense.get_senseNumber(integer=True))
for sense in senses:
if sense.get_senseNumber() is not None:
tex_entry += sense.get_senseNumber() + ") "
# definition/gloss and translation
tex_entry += tex.format_definitions(sense, font, languages)
# TODO
tex_entry += tex.format_lt(sense, font)
tex_entry += tex.format_sc(sense, font)
tex_entry += tex.format_rf(sense, font)
# example
tex_entry += tex.format_examples(sense, font)
# usage note
tex_entry += tex.format_usage_notes(sense, font)
# encyclopedic information
tex_entry += tex.format_encyclopedic_informations(sense, font)
# restriction
tex_entry += tex.format_restrictions(sense, font)
# TODO
tex_entry += tex.format_lexical_functions(lexical_entry, font)
# synonym, antonym, morphology, related form
tex_entry += tex.format_related_forms(lexical_entry, font)
# variant form
tex_entry += tex.format_variant_forms(lexical_entry, font)
# borrowed word
tex_entry += tex.format_borrowed_word(lexical_entry, font)
# etymology
tex_entry += tex.format_etymology(lexical_entry, font)
# paradigms
tex_entry += tex.format_paradigms(lexical_entry, font)
# TODO
tex_entry += tex.format_table(lexical_entry, font)
# semantic domain
tex_entry += tex.format_semantic_domains(lexical_entry, font)
# bibliography
tex_entry += tex.format_bibliography(lexical_entry, font)
# TODO
tex_entry += tex.format_picture(lexical_entry, font)
# notes
tex_entry += tex.format_notes(lexical_entry, font)
# source
tex_entry += tex.format_source(lexical_entry, font)
# status
tex_entry += tex.format_status(lexical_entry, font)
# date
tex_entry += tex.format_date(lexical_entry, font)
# Handle reserved characters and fonts
tex_entry = tex.handle_reserved(tex_entry)
tex_entry = tex.handle_quotes(tex_entry)
tex_entry = tex.handle_fv(tex_entry, font)
tex_entry = tex.handle_fn(tex_entry, font)
# Special formatting
tex_entry = tex.handle_pinyin(tex_entry)
tex_entry = tex.handle_caps(tex_entry)
return tex_entry + EOL