GeezerVison is showing github.com — bionicpython/bionicpython/bionicpython.py at master · nathfavour/bionicpython

Expand file tree

bionicpython.py

Copy path

More file actions

Latest commit

History

397 lines (272 loc) · 11.6 KB

bionicpython.py

Copy path

File metadata and controls

397 lines (272 loc) · 11.6 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

import argparse

import math

from docx import Document

import os

import argparse

import math

from docx import Document

import os

import spacy

import subprocess

import sys

import re

def process_word(word, ratio):

# Calculate the number of characters to make bold

num_chars = math.ceil(len(word) * ratio)

# Split the word into the part that should be bold and the part that shouldn't

bold_part = word[:num_chars]

normal_part = word[num_chars:]

# Create runs for the bold part and the normal part

bold_run = (bold_part, True)

normal_run = (normal_part, False)

# Return the runs as a list

return [bold_run, normal_run]

def process_document(doc_path, ratio):

output_path = os.path.splitext(doc_path)[0] + '_modified.docx'

# Check if the file path is for a .docx file

if doc_path.endswith('.docx'):

print("Already in docx format")

elif doc_path.endswith('.pdf'):

docx_path = doc_path.replace('.pdf', '.docx')

try:

# Run the conversion script as a subprocess

subprocess.run([sys.executable, 'converter.py', '--pdf', doc_path, '--docx', docx_path])

# Modify this command to run in the absolute path (with relation to this script) to converter.py

subprocess.run([sys.executable, 'converter.py', '--pdf', doc_path, '--docx', docx_path])

# Replace '.pdf' with '.docx' in the file path

doc_path = docx_path

except subprocess.CalledProcessError as e:

print("Error converting PDF:", e)

sys.exit(1)

else:

print("Files of this format are not supported yet")

print("Please use either .pdf or .docx files")

sys.exit()

# Load the spacy model for word recognition (wrap in try-except)

try:

nlp = spacy.load('en_core_web_sm')

except OSError as e:

print("Error loading spaCy model:", e)

sys.exit(1)

try:

# Open the .docx file

word_doc = Document(doc_path)

for paragraph in word_doc.paragraphs:

for run in paragraph.runs:

# Skip if the run is already bold

if run.bold:

continue

# Split the run text into words

words = run.text.split(' ')

words = [' ' + word if i != 0 else word for i, word in enumerate(words)]

# Process each word

new_runs = []

for word in words:

# Use spacy to recognize the words

doc = nlp(word)

for token in doc:

# Bolden a ratio of the characters in the word

runs = process_word(token.text, ratio)

new_runs.extend(runs)

# Clear the original run

run.text = ''

# Add new runs with the appropriate formatting

for text, is_bold in new_runs:

new_run = paragraph.add_run(text)

new_run.bold = is_bold

# Save the document (wrap in try-except)

try:

word_doc.save(output_path)

except PermissionError as e:

print("Error saving document:", e)

sys.exit(1)

except Exception as e: # Catch any other unexpected errors

print("Unexpected error processing document:", e)

sys.exit(1)

# Get the directory and filename from the input path

dir_name, file_name = os.path.split(doc_path)

# Prepend 'processed_' to the filename

new_file_name = 'processed_' + file_name

# Combine the directory and new filename to get the output path

# output_path = os.path.splitext(doc_path)[0] + '_modified.docx'

print(output_path)

def main():

parser = argparse.ArgumentParser()

parser.add_argument('doc_path', help='Path to the .docx file')

parser.add_argument('--ratio', type=float, default=0.5, help='Ratio of characters to make bold')

args = parser.parse_args()

process_document(args.doc_path, args.ratio)

if __name__ == '__main__':

main()

# def process_document(doc_path, ratio):

# # Check if the file path is for a .docx file

# if not doc_path.endswith('.docx'):

# print("Invalid file format. Please provide a .docx file.")

# return

# # Load the spacy model for word recognition

# nlp = spacy.load('en_core_web_sm')

# # Open the .docx file

# doc = Document(doc_path)

# for paragraph in doc.paragraphs:

# for run in paragraph.runs:

# # Skip if the run is already bold

# if run.bold:

# continue

# # Split the run text into words

# words = run.text.split()

# # Process each word

# new_runs = []

# for word in words:

# # Use spacy to recognize the words

# doc = nlp(word)

# for token in doc:

# # Bolden a ratio of the characters in the word

# runs = process_word(token.text, ratio)

# new_runs.extend(runs)

# # Clear the original run

# run.text = ''

# # Add new runs with the appropriate formatting

# for text, is_bold in new_runs:

# new_run = paragraph.add_run(text)

# new_run.bold = is_bold

# # Get the directory and filename from the input path

# dir_name, file_name = os.path.split(doc_path)

# # Prepend 'processed_' to the filename

# new_file_name = 'processed_' + file_name

# # Combine the directory and new filename to get the output path

# output_path = os.path.join(dir_name, new_file_name)

# doc.save(output_path)

# def process_word(word, ratio):

# # Calculate the number of characters to make bold

# num_chars = math.ceil(len(word) * ratio)

# # Make the specified number of characters bold

# bold_word = word[:num_chars] + word[num_chars:].bold()

# return bold_word

# def process_document(doc_path, ratio):

# # Check if the file path is for a .docx file

# if not doc_path.endswith('.docx'):

# print("Invalid file format. Please provide a .docx file.")

# return

# # Load the spacy model for word recognition

# nlp = spacy.load('en_core_web_sm')

# # Open the .docx file

# doc = Document(doc_path)

# for paragraph in doc.paragraphs:

# for run in paragraph.runs:

# # Skip if the run is already bold

# if run.bold:

# continue

# # Split the run text into words

# words = run.text.split()

# # Process each word

# new_words = []

# for word in words:

# # Use spacy to recognize the words

# doc = nlp(word)

# for token in doc:

# # Bolden a ratio of the characters in the word

# bold_word = process_word(token.text, ratio)

# new_words.append(bold_word)

# # Replace the run text with the processed words

# run.text = ' '.join(new_words)

# print("processed another paragraph...")

# # Get the directory and filename from the input path

# dir_name, file_name = os.path.split(doc_path)

# # Prepend 'processed_' to the filename

# new_file_name = 'processed_' + file_name

# # Combine the directory and new filename to get the output path

# output_path = os.path.join(dir_name, new_file_name)

# doc.save(output_path)

# def main():

# parser = argparse.ArgumentParser()

# parser.add_argument('doc_path', help='Path to the .docx file')

# parser.add_argument('--ratio', type=float, default=0.5, help='Ratio of characters to make bold')

# args = parser.parse_args()

# process_document(args.doc_path, args.ratio)

# if __name__ == '__main__':

# main()

# python bionic.py /path/to/your/document.docx

# def process_word(word, ratio):

# # Calculate the number of characters to make bold

# num_bold_chars = math.ceil(len(word) * ratio)

# # Create a new run for each part of the word

# bold_run = word[:num_bold_chars]

# normal_run = word[num_bold_chars:]

# return bold_run, normal_run

# # def process_document(doc_path, ratio):

# # doc = Document(doc_path)

# # for paragraph in doc.paragraphs:

# # for run in paragraph.runs:

# # # Skip if the run is already bold

# # if run.bold:

# # continue

# # # Split the run text into words

# # words = run.text.split()

# # # Process each word

# # new_words = []

# # for word in words:

# # bold_run, normal_run = process_word(word, ratio)

# # new_words.append(bold_run)

# # new_words.append(normal_run)

# # # Replace the run text with the processed words

# # run.text = ' '.join(new_words)

# # doc.save('processed_' + doc_path)

# # def process_document(doc_path, ratio):

# # doc = Document(doc_path)

# # for paragraph in doc.paragraphs:

# # for run in paragraph.runs:

# # # Skip if the run is already bold

# # if run.bold:

# # continue

# # # Split the run text into words

# # words = run.text.split()

# # # Process each word

# # new_words = []

# # for word in words:

# # bold_run, normal_run = process_word(word, ratio)

# # new_words.append(bold_run)

# # new_words.append(normal_run)

# # # Replace the run text with the processed words

# # run.text = ' '.join(new_words)

# # # Get the directory and filename from the input path

# # dir_name, file_name = os.path.split(doc_path)

# # # Prepend 'processed_' to the filename

# # new_file_name = 'processed_' + file_name

# # # Combine the directory and new filename to get the output path

# # output_path = os.path.join(dir_name, new_file_name)

# # doc.save(output_path)

# def process_document(doc_path, ratio):

# doc = Document(doc_path)

# new_doc = Document()

# for paragraph in doc.paragraphs:

# new_paragraph = new_doc.add_paragraph()

# for run in paragraph.runs:

# # Skip if the run is already bold

# if run.bold:

# continue

# # Split the run text into words

# words = run.text.split()

# # Process each word

# for word in words:

# bold_run_text, normal_run_text = process_word(word, ratio)

# # Add new runs to the new paragraph

# if bold_run_text:

# bold_run = new_paragraph.add_run(bold_run_text)

# bold_run.bold = True

# if normal_run_text:

# normal_run = new_paragraph.add_run(normal_run_text)

# # Get the directory and filename from the input path

# dir_name, file_name = os.path.split(doc_path)

# # Prepend 'processed_' to the filename

# new_file_name = 'processed_' + file_name

# # Combine the directory and new filename to get the output path

# output_path = os.path.join(dir_name, new_file_name)

# new_doc.save(output_path)

# def main():

# parser = argparse.ArgumentParser()

# parser.add_argument('doc_path', help='Path to the .docx file')

# parser.add_argument('--ratio', type=float, default=0.5, help='Ratio of characters to make bold')

# args = parser.parse_args()

# process_document(args.doc_path, args.ratio)

# if __name__ == '__main__':

# main()