110 lines
3.5 KiB
Python
110 lines
3.5 KiB
Python
import csv
|
|
import os
|
|
import re
|
|
|
|
|
|
def remove_links(definitions: str) -> str:
|
|
definitions = re.sub(r"\[\[([^\|\]\]]*)\]\]", r"\1", definitions)
|
|
definitions = re.sub(r"\[\[[^\[\[]*\|([^\|\]\]]*)\]\]", r"\1", definitions)
|
|
return definitions
|
|
|
|
|
|
def replace_asterisks_with_italics(text: str) -> str:
|
|
is_odd = True
|
|
result = ""
|
|
|
|
for char in text:
|
|
if char == "*":
|
|
if is_odd:
|
|
result += "<i>"
|
|
else:
|
|
result += "</i>"
|
|
is_odd = not is_odd
|
|
else:
|
|
result += char
|
|
|
|
return result
|
|
|
|
|
|
def extract_example_sentences(content: str) -> str:
|
|
sentences = [line[2:].strip() for line in content.split("\n")[1:] if line.strip()]
|
|
joined = "\n".join([f"<li>{replace_asterisks_with_italics(sentence)}</li>" for sentence in sentences])
|
|
return f"<ul>{joined}</ul>"
|
|
|
|
|
|
def read_markdown_file(file_path: str, filename: str) -> tuple[str, str, str] | None:
|
|
try:
|
|
with open(file_path, "r", encoding="utf-8") as f:
|
|
content = f.read()
|
|
|
|
word = os.path.splitext(filename)[0]
|
|
|
|
content_parts = content.split("??")
|
|
if len(content_parts) <= 1:
|
|
raise Exception("No delimiter found")
|
|
|
|
definitions = content_parts[1]
|
|
|
|
examples = extract_example_sentences(content_parts[0])
|
|
|
|
filtered_lines = []
|
|
for line in definitions.split("\n"):
|
|
line = line.strip()
|
|
if line.startswith(("n.", "adj.", "adv.", "v.", "prep.")):
|
|
filtered_lines.append(line)
|
|
|
|
definitions = "\n".join(filtered_lines)
|
|
definitions = remove_links(definitions)
|
|
return word, definitions, examples
|
|
except Exception as e:
|
|
print(f"Error reading {file_path}: {e}")
|
|
return None
|
|
|
|
|
|
def walk_directory(directory=".") -> list[tuple[str, str, str]]:
|
|
"""
|
|
Recursively reads all .md files in the given directory and its subdirectories.
|
|
Prints the filename and contents of each file.
|
|
|
|
Args:
|
|
directory (str): The directory to start searching from. Defaults to current directory.
|
|
"""
|
|
word_definitions = []
|
|
for root, dirs, files in os.walk(directory):
|
|
for file in files:
|
|
if not file.endswith(".md"):
|
|
continue
|
|
|
|
file_path = os.path.join(root, file)
|
|
result = read_markdown_file(file_path, file)
|
|
if not result:
|
|
continue
|
|
|
|
word, definitions, examples = result
|
|
word_definitions.append((word, definitions, examples))
|
|
|
|
return word_definitions
|
|
|
|
|
|
if __name__ == "__main__":
|
|
word_definitions = walk_directory(".")
|
|
# Sort word_definitions alphabetically by word (first element of each tuple)
|
|
word_definitions.sort(key=lambda x: x[0])
|
|
|
|
# Write to CSV file
|
|
with open("word_definitions.csv", "w", encoding="utf-8", newline="") as csvfile:
|
|
csv_writer = csv.writer(csvfile)
|
|
# Write header row
|
|
# Write each word and its definitions to the CSV file
|
|
for word, definitions, examples in word_definitions:
|
|
csv_writer.writerow([word, definitions, examples])
|
|
|
|
print(len(word_definitions))
|
|
|
|
# print(f"Successfully wrote {len(word_definitions)} words to word_definitions.csv")
|
|
# # Write to text file
|
|
# with open("word_definitions.txt", "w", encoding="utf-8") as textfile:
|
|
# # Write each word and its definitions to the text file
|
|
# for word, definitions in word_definitions:
|
|
# textfile.write(f"{word},{definitions}\n\n")
|