Permalink
Cannot retrieve contributors at this time
Name already in use
A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
genetics-jargon-counter/extract-concepts.py
Go to fileThis commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
67 lines (65 sloc)
2.12 KB
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
"""Extract concepts from XML file and output one concept per line""" | |
from lxml import etree | |
from sys import argv | |
with open(argv[1], "r") as file_handle: | |
xml = file_handle.read() | |
root = etree.XML(xml) | |
# We can't use XPath here since we need both the tags elements with | |
# <b> and without. | |
lines = [] | |
for elem in root.findall('.//text'): | |
line = list(elem.itertext())[0] | |
# Remove junk characters | |
for char in u'\t\n\xa0\xad\u2013\u2018\u2019\u2010': | |
line = line.replace(char, '') | |
lines += [line] | |
# Extract tags between "Key terms and concepts:" and "Practise | |
# problems:" | |
start = -1 | |
end = -1 | |
for i in range(len(lines)): | |
if "Key terms and concepts" in lines[i]: | |
start = i | |
elif "Practice problems" in lines[i]: | |
end = i | |
lines = [lines[i] for i in range(start+1, end-1)] | |
# Split lines with leading closing paranthesis | |
split_lines = [] | |
for line in lines: | |
if line[0] == ')': | |
split_lines += [line[:2]] | |
if len(line) > 2: | |
split_lines += [line[2:]] | |
else: | |
split_lines += [line] | |
lines = split_lines | |
# Join together lines beginning with lowercase characters, and also group | |
# lines containing matching parantheses | |
prev_line = lines[0] | |
joined_lines = [prev_line] | |
active_parens = False | |
i = 1 | |
for line in [lines[i] for i in range(1, len(lines))]: | |
if '(' in line and ')' not in line: | |
active_parens = True | |
if line[0].islower() or active_parens: | |
joined_lines.pop() | |
joined_line = prev_line + line | |
else: | |
joined_line = line | |
if ')' in line: | |
active_parens = False | |
joined_lines += [joined_line] | |
prev_line = joined_lines[-1] | |
# Remove trailing spaces and convert from unicode to string | |
lines = [] | |
import unicodedata | |
for line in joined_lines: | |
line = line.strip() # Remove padded spaces | |
if line != '': # Ignore blank lines | |
lines += [unicodedata.normalize('NFKD', line).encode('ascii','ignore') | |
+ '\r\n'] # Add newline | |
# Write output to file | |
output_file_name = argv[1][:-4] + '-extracted.txt' | |
with open(output_file_name, "w") as file_handle: | |
file_handle.writelines(lines) |