generic/structure_assignment
16
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

IssueID #1487: fixed basic bugs

Browse Source
This commit is contained in:
Cyprian Laskowski 2021-01-13 19:07:35 +01:00
parent 364acf58bc
commit aae67a3070
3 changed files with 9 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
scripts/merge_dictionaries.py
View File

@ -1,4 +1,5 @@
import argparse
import re
import lxml.etree as lxml
arg_parser = argparse.ArgumentParser(description='Split input TEI into single and multiple token units.')
@ -14,11 +15,11 @@ def get_entries(input_file_name):
return list(lxml.parse(input_file_name).getroot())
entries = get_entries(single_file_name) + get_entries(multiple_file_name)
sort(entries, key=lambda entry: int(re.search('^s(\d+)\.\d+$', entry.get('xml:id')).group(1)))
entries.sort(key=lambda entry: int(re.search('^s(\d+)\.\d+$', entry.get('sid')).group(1)))
root = lxml.Element('dictionary')
for entry in entries:
del entry.attrib['xml:id']
del entry.attrib['sid']
root.append(entry)
tree = lxml.ElementTree(root)
tree.write(output_file_name, encoding='UTF-8', pretty_print=True)

8
scripts/pipeline2.py
View File

@ -43,7 +43,7 @@ def run_pipeline(input_tei_file_name, output_lexicon_file_name, output_structure
def split_tei_input(input_file_name, single_file_name, multiple_file_name):
print('Splitting TEI input file ...')
split_command = ' '.join(['python', TEI_SPLIT_SCRIPT_NAME, '--input', input_file_name, '--single', single_file_name, '--multiple', multiple_file_name])
split_command = ' '.join(['python', TEI_SPLIT_SCRIPT_NAME, '-infile', input_file_name, '-single', single_file_name, '-multiple', multiple_file_name])
os.system(split_command)
def run_mwe_extraction(structure_file_name, tei_file_name, mwe_csv_file_name):
@ -70,12 +70,12 @@ def run_structure_creation(input_file_name, tei_file_name, output_file_name):
def run_dictionary_conversion(tei_file_name, xml_file_name):
print('Converting to dictionary xml format ...')
convert_command = ' '.join(['python', TEI_DICTIONARY_SCRIPT_NAME, '-infile', tei_file_name, '-outfile', xml_file_name, '--keepids', 'true'])
convert_command = ' '.join(['python', TEI_DICTIONARY_SCRIPT_NAME, '-infile', tei_file_name, '-outfile', xml_file_name])
os.system(convert_command)
def merge_dictionaries(single_file_name, multiple_file_name, joint_file_name):
def merge_dictionaries(single_file_name, multiple_file_name, output_file_name):
print('Merging dictionary files ...')
merge_command = ' '.join(['python', DICTIONARY_MERGE_SCRIPT_NAME, '-single', single_file_name, '--multiple', multiple_file_name, '--joint', joint_file_name])
merge_command = ' '.join(['python', DICTIONARY_MERGE_SCRIPT_NAME, '-single', single_file_name, '-multiple', multiple_file_name, '-outfile', output_file_name])
os.system(merge_command)
def validate_dictionary(dictionary_file_name):

4
scripts/split_tei.py
View File

@ -19,7 +19,7 @@ def count_tokens(paragraph):
tree = lxml.parse(input_file_name)
root = tree.getroot()
paragraphs = xpath_find('.//tei:p')
paragraphs = xpath_find(root, './/tei:p')
for paragraph in paragraphs:
if (count_tokens(paragraph) > 1):
paragraph.getparent().remove(paragraph)
@ -27,7 +27,7 @@ tree.write(single_file_name, encoding='UTF-8', pretty_print=True)
tree = lxml.parse(input_file_name)
root = tree.getroot()
paragraphs = xpath_find('.//tei:p')
paragraphs = xpath_find(root, './/tei:p')
for paragraph in paragraphs:
if (count_tokens(paragraph) == 1):
paragraph.getparent().remove(paragraph)