forked from hirusha-adi/docx-search
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
c466b8f
commit f54cb59
Showing
2 changed files
with
107 additions
and
114 deletions.
There are no files selected for viewing
This file was deleted.
Oops, something went wrong.
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,24 +1,116 @@ | ||
import argparse | ||
import os | ||
from docx_search import docx_search | ||
import logging | ||
from docx import Document | ||
from concurrent.futures import ThreadPoolExecutor | ||
from datetime import datetime | ||
import tkinter as tk | ||
from tkinter import filedialog | ||
|
||
# Configure logger | ||
if not os.path.isdir('logs'): | ||
os.mkdir('logs') | ||
|
||
def main(): | ||
parser = argparse.ArgumentParser(description='Search for a word in .docx files in a specified directory.') | ||
parser.add_argument('--dir', dest='target_dir', type=str, default=os.getcwd(), | ||
help='The target directory to search for .docx files. Defaults to the current working directory.') | ||
parser.add_argument('--word', dest='target_word', type=str, | ||
help='The word to search for in the documents. If not provided, the user will be prompted.') | ||
args = parser.parse_args() | ||
log_format = '(%(asctime)s) [%(levelname)s] %(message)s' | ||
log_file_name = datetime.now().strftime('%Y-%m-%d_%H-%M-%S') + '.log' | ||
log_file_path = os.path.join(os.getcwd(), "logs", log_file_name) | ||
|
||
target_dir = args.target_dir | ||
target_word = args.target_word | ||
logging.basicConfig(level=logging.DEBUG, format=log_format, handlers=[ | ||
logging.FileHandler(log_file_path, encoding='utf-8'), | ||
logging.StreamHandler() | ||
]) | ||
|
||
if not target_word: | ||
target_word = input("Enter the word to search for: ") | ||
logger = logging.getLogger(__name__) | ||
|
||
docx_search(target_dir=target_dir, target_word=target_word) | ||
def __check(fpath, target): | ||
try: | ||
doc = Document(fpath) | ||
for paragraph in doc.paragraphs: | ||
if target in paragraph.text: | ||
return True | ||
return False | ||
except Exception as e: | ||
logger.error("Error processing %s: %s" % (fpath, e)) | ||
return False | ||
|
||
def __process_file(file): | ||
fname, target = file | ||
fpath = os.path.join(os.getcwd(), fname) | ||
if __check(fpath, target): | ||
logger.info("'%s' found in %s" % (target, fname)) | ||
return fname | ||
else: | ||
logger.debug("'%s' not found in %s" % (target, fname)) | ||
return None | ||
|
||
def perform_search(target_dir=None, target_word=None): | ||
if target_word is None or target_word == '': | ||
raise ValueError("target_word cannot be None or an empty string. Please pass in a valid value.") | ||
|
||
if target_dir is None: | ||
target_dir = os.getcwd() | ||
|
||
file_list = [(fname, target_word) for fname in os.listdir(target_dir) if fname.endswith(".docx")] | ||
|
||
results = [] | ||
with ThreadPoolExecutor() as executor: | ||
results = list(executor.map(__process_file, file_list)) | ||
|
||
return [result for result in results if result is not None] | ||
|
||
class GUIFrontend: | ||
def __init__(self, master): | ||
self.master = master | ||
self.master.title("Document Search App") | ||
|
||
self.target_word_label = tk.Label(master, text="Target Word:") | ||
self.target_word_label.pack() | ||
|
||
self.target_word_entry = tk.Entry(master) | ||
self.target_word_entry.pack() | ||
|
||
self.browse_button = tk.Button(master, text="Browse", command=self.browse_directory) | ||
self.browse_button.pack() | ||
|
||
self.search_button = tk.Button(master, text="Search", command=self.search_documents) | ||
self.search_button.pack() | ||
|
||
self.result_listbox = tk.Listbox(master) | ||
self.result_listbox.pack() | ||
self.result_listbox.bind("<Double-Button-1>", self.open_file) | ||
|
||
# Initialize target_directory | ||
self.target_directory = None | ||
|
||
def browse_directory(self): | ||
directory = filedialog.askdirectory() | ||
if directory: | ||
self.target_directory = directory | ||
|
||
def search_documents(self): | ||
target_word = self.target_word_entry.get() | ||
if not target_word: | ||
tk.messagebox.showerror("Error", "Target word cannot be empty.") | ||
return | ||
|
||
if self.target_directory is None: | ||
self.target_directory = os.getcwd() | ||
|
||
results = perform_search(target_dir=self.target_directory, target_word=target_word) | ||
self.update_result_list(results) | ||
|
||
def update_result_list(self, results): | ||
self.result_listbox.delete(0, tk.END) | ||
for result in results: | ||
self.result_listbox.insert(tk.END, result) | ||
|
||
def open_file(self, event): | ||
selected_item = self.result_listbox.curselection() | ||
if selected_item: | ||
file_name = self.result_listbox.get(selected_item) | ||
file_path = os.path.join(self.target_directory, file_name) | ||
os.startfile(file_path) | ||
|
||
if __name__ == "__main__": | ||
main() | ||
root = tk.Tk() | ||
app = GUIFrontend(root) | ||
root.mainloop() |