| 1 |
import keywords as kw |
| 2 |
import word_iterator as wi |
| 3 |
import header as hd |
| 4 |
import color_print as cp |
| 5 |
|
| 6 |
|
| 7 |
class Counter: |
| 8 |
""" |
| 9 |
Class that analyzes a source code and counts word counts |
| 10 |
""" |
| 11 |
|
| 12 |
def __init__(self, filename, color_print=False, verb_char=None): |
| 13 |
self.word_iter = wi.WordIterator(filename) # source of words that will be analyzed |
| 14 |
if verb_char is not None: |
| 15 |
self.word_iter.add_separator(verb_char) |
| 16 |
self.verb_char = verb_char # used for inline verbatim text |
| 17 |
self.color_print = color_print # input text will be printed(with colors) |
| 18 |
self.printer = cp.Printer() |
| 19 |
self.regular_words_count = 0 |
| 20 |
self.header_words_count = 0 |
| 21 |
self.caption_words_count = 0 |
| 22 |
self.figure_float_count = 0 |
| 23 |
self.math_inline_count = 0 |
| 24 |
self.math_count = 0 |
| 25 |
self.all_headers = [] |
| 26 |
""" |
| 27 |
Three possible types of __context: |
| 28 |
1) regular-text (implicit) |
| 29 |
2) headers |
| 30 |
3) captions |
| 31 |
""" |
| 32 |
self.__context = "regular-text" |
| 33 |
|
| 34 |
def run(self): |
| 35 |
""" |
| 36 |
Main method of the class |
| 37 |
Loads all words and initializes the analysis |
| 38 |
""" |
| 39 |
pair = self.word_iter.read() |
| 40 |
while pair is not None and pair[0] != "\\bye": |
| 41 |
self.__process_word(pair) |
| 42 |
pair = self.word_iter.read() |
| 43 |
if pair is not None: |
| 44 |
self.print_keyword(pair) |
| 45 |
self.print_irrelevant_word(("", "\n")) |
| 46 |
|
| 47 |
def print_result(self): |
| 48 |
""" |
| 49 |
Generates formatted output of the counter |
| 50 |
""" |
| 51 |
print("Text words summary: " + str(self.regular_words_count)) |
| 52 |
print("Header words summary: " + str(self.header_words_count)) |
| 53 |
print("Caption and notes words summary: " + str(self.caption_words_count)) |
| 54 |
print("Headers summary: " + str(len(self.all_headers))) |
| 55 |
print("Figure/float count: " + str(self.figure_float_count)) |
| 56 |
print("Inline math formulae count: " + str(self.math_inline_count)) |
| 57 |
print("Math formulae count: " + str(self.math_count)) |
| 58 |
print("Subcounts: (header-words-count + text-words-count + caption-words-count)") |
| 59 |
for header in self.all_headers: |
| 60 |
print(header) |
| 61 |
|
| 62 |
def print_counted_word(self, pair): |
| 63 |
""" |
| 64 |
Prints word that was counted. The color depends on category of the word. |
| 65 |
""" |
| 66 |
if not self.color_print: |
| 67 |
return |
| 68 |
if self.__context == "regular-text": |
| 69 |
self.printer.blue(pair[0]+pair[1]) |
| 70 |
elif self.__context == "header": |
| 71 |
self.printer.cyan(pair[0]+pair[1]) |
| 72 |
elif self.__context == "caption": |
| 73 |
self.printer.green(pair[0]+pair[1]) |
| 74 |
|
| 75 |
def print_keyword(self, pair): |
| 76 |
""" |
| 77 |
Prints keyword - word with red color |
| 78 |
""" |
| 79 |
if not self.color_print: |
| 80 |
return |
| 81 |
self.printer.red(pair[0]+pair[1]) |
| 82 |
|
| 83 |
def print_irrelevant_word(self, pair): |
| 84 |
""" |
| 85 |
Prints words that wasn't counted and are not important for our functionality, like commentary words etc... |
| 86 |
""" |
| 87 |
if not self.color_print: |
| 88 |
return |
| 89 |
self.printer.white(pair[0]+pair[1]) |
| 90 |
|
| 91 |
def __process_word(self, pair): |
| 92 |
""" |
| 93 |
Decides how to treat with word from argument |
| 94 |
""" |
| 95 |
if len(pair[0]) == 0 or pair[0] == "\n": # empty word or newline |
| 96 |
self.print_irrelevant_word(pair) |
| 97 |
elif pair[0] == "%": |
| 98 |
self.print_irrelevant_word(pair) |
| 99 |
self.__skip_commentary() |
| 100 |
elif pair[0] == "{": |
| 101 |
self.print_irrelevant_word(pair) |
| 102 |
self.__load_curly_brackets() |
| 103 |
elif pair[0] == "$": |
| 104 |
self.print_keyword(pair) |
| 105 |
self.__load_inline_formulae() |
| 106 |
elif pair[0] == "$$": |
| 107 |
self.print_keyword(pair) |
| 108 |
self.__load_formulae() |
| 109 |
elif self.verb_char is not None and pair[0] == self.verb_char: |
| 110 |
self.print_keyword(pair) |
| 111 |
self.__load_verbatim(self.verb_char) |
| 112 |
elif self.__is_keyword(pair[0]): |
| 113 |
self.__process_keyword(pair) |
| 114 |
else: |
| 115 |
self.__process_text_word(pair) |
| 116 |
|
| 117 |
def __process_keyword(self, pair): |
| 118 |
""" |
| 119 |
Treats with keywords. |
| 120 |
Calls action on known keywords that are important for the counter |
| 121 |
If keyword is unknown it is skipped |
| 122 |
""" |
| 123 |
word, arg = self.__split_keyword(pair[0]) |
| 124 |
self.print_keyword((word, '')) |
| 125 |
if arg is None: |
| 126 |
self.print_irrelevant_word(('', pair[1])) |
| 127 |
else: |
| 128 |
self.print_irrelevant_word((arg, pair[1])) |
| 129 |
if word == '\\tit': |
| 130 |
self.all_headers.append(hd.Header("title")) |
| 131 |
self.__load_header() |
| 132 |
elif word == '\\chap': |
| 133 |
self.all_headers.append(hd.Header("chapter")) |
| 134 |
self.__skip_brackets("[", "]") |
| 135 |
self.__load_header() |
| 136 |
elif word == '\\sec': |
| 137 |
self.all_headers.append(hd.Header("section")) |
| 138 |
self.__skip_brackets("[", "]") |
| 139 |
self.__load_header() |
| 140 |
elif word == '\\secc': |
| 141 |
self.all_headers.append(hd.Header("subsection")) |
| 142 |
self.__skip_brackets("[", "]") |
| 143 |
self.__load_header() |
| 144 |
elif word == '\\begitems': |
| 145 |
self.__load_list() |
| 146 |
elif word == '\\caption': |
| 147 |
self.__skip_brackets("[", "]") |
| 148 |
self.__load_caption() |
| 149 |
elif word == '\\fnote' or word == '\\fnotetext' or word == '\\mnote': |
| 150 |
self.__load_footnote() |
| 151 |
elif word in kw.keywords_list: |
| 152 |
if word in kw.floats_keywords: |
| 153 |
self.figure_float_count += 1 |
| 154 |
self.__read_arguments(word) |
| 155 |
elif word == '\\begtt': |
| 156 |
self.__skip_commentary() |
| 157 |
self.__load_verbatim() |
| 158 |
elif word == '\\verbchar' or word == '\\activettchar': # keywords with same functionality |
| 159 |
self.__set_verb_char(word, arg, pair[1]) |
| 160 |
elif word == '\\code': |
| 161 |
self.__load_code_verbatim() |
| 162 |
elif word in kw.logos: |
| 163 |
self.__load_logo(word, arg, pair[1]) |
| 164 |
else: |
| 165 |
pass # skip unknown keywords |
| 166 |
|
| 167 |
def __process_text_word(self, pair): |
| 168 |
""" |
| 169 |
Increases word counts based on the word location - word context |
| 170 |
""" |
| 171 |
# word with only one character that is not alphanumeric won't be counted as word |
| 172 |
if len(pair[0]) == 0: |
| 173 |
self.print_irrelevant_word(pair) |
| 174 |
elif len(pair[0]) == 1 and not pair[0].isalnum(): |
| 175 |
self.print_irrelevant_word(pair) |
| 176 |
elif self.__context == "regular-text": |
| 177 |
self.print_counted_word(pair) |
| 178 |
self.regular_words_count += 1 |
| 179 |
if len(self.all_headers): |
| 180 |
self.all_headers[-1].add_text_word() |
| 181 |
elif self.__context == "header": |
| 182 |
self.print_counted_word(pair) |
| 183 |
self.header_words_count += 1 |
| 184 |
self.all_headers[-1].add_header_word(pair[0]) |
| 185 |
elif self.__context == "caption": |
| 186 |
self.print_counted_word(pair) |
| 187 |
self.caption_words_count += 1 |
| 188 |
if len(self.all_headers): |
| 189 |
self.all_headers[-1].add_caption_word() |
| 190 |
|
| 191 |
@staticmethod |
| 192 |
def __is_keyword(word): |
| 193 |
""" |
| 194 |
Decides whether word is keyword or not |
| 195 |
""" |
| 196 |
if len(word) >= 3: |
| 197 |
if word[0] == '\\' and word[1].isalpha() and word[2].isalpha(): |
| 198 |
return True |
| 199 |
return False |
| 200 |
|
| 201 |
@staticmethod |
| 202 |
def __split_keyword(word): |
| 203 |
""" |
| 204 |
Splits word to two part - keyword and its argument |
| 205 |
For example: |
| 206 |
'\verbchar"' will be splitted into pair: '\verbchar', '"' |
| 207 |
""" |
| 208 |
for i in range(1, len(word)): |
| 209 |
if not word[i].isalpha(): |
| 210 |
return word[:i], word[i:] |
| 211 |
return word, None |
| 212 |
|
| 213 |
def __load_header(self): |
| 214 |
""" |
| 215 |
Loads header |
| 216 |
It reads the source code until new line occurs. |
| 217 |
In case of ^^J at the end of the line it reads until next new line occurs. |
| 218 |
""" |
| 219 |
orig_context = self.__context |
| 220 |
self.__context = 'header' |
| 221 |
pair = self.word_iter.read() |
| 222 |
skip_new_line = False |
| 223 |
while pair is not None and pair[0] != "\\bye": |
| 224 |
if not len(pair[0]): |
| 225 |
self.print_irrelevant_word(pair) |
| 226 |
elif pair[0] == "\n": |
| 227 |
self.print_irrelevant_word(pair) |
| 228 |
if not skip_new_line: |
| 229 |
self.__context = orig_context |
| 230 |
return |
| 231 |
skip_new_line = False |
| 232 |
elif pair[0] == "^^J": |
| 233 |
self.print_irrelevant_word(pair) |
| 234 |
skip_new_line = True |
| 235 |
else: |
| 236 |
self.__process_word(pair) |
| 237 |
skip_new_line = False |
| 238 |
pair = self.word_iter.read() |
| 239 |
self.__context = orig_context |
| 240 |
if pair is not None: |
| 241 |
self.__process_keyword(pair) |
| 242 |
|
| 243 |
def __load_list(self): |
| 244 |
""" |
| 245 |
Loads list - words that are surrounded by '\begitems' and '\enditems' |
| 246 |
""" |
| 247 |
pair = self.word_iter.read() |
| 248 |
while pair is not None and pair[0] != "\\enditems": |
| 249 |
if pair[0] != "*": |
| 250 |
self.__process_word(pair) |
| 251 |
else: |
| 252 |
self.print_irrelevant_word(pair) |
| 253 |
pair = self.word_iter.read() |
| 254 |
if pair is None: |
| 255 |
raise Exception("No list ending found - \\enditems") |
| 256 |
else: |
| 257 |
self.print_keyword(pair) |
| 258 |
|
| 259 |
def __load_caption(self): |
| 260 |
""" |
| 261 |
Loads caption - words until EOL |
| 262 |
""" |
| 263 |
orig_context = self.__context |
| 264 |
self.__context = 'caption' |
| 265 |
pair = self.word_iter.read() |
| 266 |
while pair is not None and pair[0] != "\\bye": |
| 267 |
if pair[0] == "\n": |
| 268 |
self.print_irrelevant_word(pair) |
| 269 |
self.__context = orig_context |
| 270 |
return |
| 271 |
else: |
| 272 |
self.__process_word(pair) |
| 273 |
pair = self.word_iter.read() |
| 274 |
self.__context = orig_context |
| 275 |
if pair is not None: |
| 276 |
self.print_keyword(pair) |
| 277 |
|
| 278 |
def __load_footnote(self): |
| 279 |
""" |
| 280 |
Loads footnote(block in curly brackets) |
| 281 |
""" |
| 282 |
orig_context = self.__context |
| 283 |
self.__context = 'caption' |
| 284 |
pair = self.word_iter.read() |
| 285 |
if pair is None: |
| 286 |
raise Exception("No opening curly bracket found!") |
| 287 |
while len(pair[0]) == 0 or pair[0].isspace(): |
| 288 |
self.print_irrelevant_word(pair) |
| 289 |
pair = self.word_iter.read() |
| 290 |
if pair[0] != "{": |
| 291 |
self.__context = orig_context |
| 292 |
self.word_iter.push_back(pair) |
| 293 |
return |
| 294 |
self.print_irrelevant_word(pair) |
| 295 |
self.__load_curly_brackets() |
| 296 |
self.__context = orig_context |
| 297 |
|
| 298 |
def __load_formulae(self): |
| 299 |
""" |
| 300 |
Loads math formulae($$ as separator) |
| 301 |
""" |
| 302 |
pair = self.word_iter.read() |
| 303 |
while pair is not None and pair[0] != "$$": |
| 304 |
self.print_irrelevant_word(pair) |
| 305 |
pair = self.word_iter.read() |
| 306 |
if pair is None: |
| 307 |
raise Exception("No end of math formulae found!") |
| 308 |
else: |
| 309 |
self.print_keyword(pair) |
| 310 |
self.math_count += 1 |
| 311 |
|
| 312 |
def __load_inline_formulae(self): |
| 313 |
""" |
| 314 |
Loads inline math formulae($ as separator) |
| 315 |
""" |
| 316 |
pair = self.word_iter.read() |
| 317 |
while pair is not None and pair[0] != "$": |
| 318 |
self.print_irrelevant_word(pair) |
| 319 |
pair = self.word_iter.read() |
| 320 |
self.math_inline_count += 1 |
| 321 |
if pair is None: |
| 322 |
raise Exception("No end of inline math formulae found!") |
| 323 |
else: |
| 324 |
self.print_keyword(pair) |
| 325 |
|
| 326 |
def __load_verbatim(self, ending="\\endtt", keyword_print=True): |
| 327 |
""" |
| 328 |
Reads words until ending(param) word occurs. |
| 329 |
These words are processed as regular word(not keywords etc...) |
| 330 |
""" |
| 331 |
pair = self.word_iter.read() |
| 332 |
while pair is not None and ending != pair[0]: |
| 333 |
self.__process_text_word(pair) |
| 334 |
pair = self.word_iter.read() |
| 335 |
if pair is None: |
| 336 |
raise Exception("Verbatim text not terminated!") |
| 337 |
else: |
| 338 |
if keyword_print: |
| 339 |
self.print_keyword(pair) |
| 340 |
else: |
| 341 |
self.print_irrelevant_word(pair) |
| 342 |
|
| 343 |
def __load_code_verbatim(self): |
| 344 |
""" |
| 345 |
In case of verbatim using "\code" keyword |
| 346 |
""" |
| 347 |
pair = self.word_iter.read() |
| 348 |
while len(pair[0]) == 0 or pair[0].isspace(): |
| 349 |
self.print_irrelevant_word(pair) |
| 350 |
pair = self.word_iter.read() |
| 351 |
if pair[0] != "{": |
| 352 |
raise Exception("\\Code must be followed be opening curly bracket('{')!") |
| 353 |
self.print_irrelevant_word(pair) |
| 354 |
self.__load_verbatim("}", False) |
| 355 |
|
| 356 |
def __load_logo(self, logo, arg, sep): |
| 357 |
""" |
| 358 |
Checks whether logo keyword is followed by slash etc... |
| 359 |
""" |
| 360 |
if arg != '/' or len(sep) > 0: |
| 361 |
pass |
| 362 |
elif self.__context == "regular-text": |
| 363 |
self.regular_words_count += 1 |
| 364 |
if len(self.all_headers): |
| 365 |
self.all_headers[-1].add_text_word() |
| 366 |
elif self.__context == "header": |
| 367 |
self.header_words_count += 1 |
| 368 |
self.all_headers[-1].add_header_word(logo) |
| 369 |
elif self.__context == "caption": |
| 370 |
self.caption_words_count += 1 |
| 371 |
if len(self.all_headers): |
| 372 |
self.all_headers[-1].add_caption_word() |
| 373 |
|
| 374 |
def __set_verb_char(self, word, arg, sep): |
| 375 |
""" |
| 376 |
Loads new character for inline verbatim |
| 377 |
""" |
| 378 |
if arg is not None and len(arg) == 1: |
| 379 |
self.verb_char = arg |
| 380 |
self.word_iter.add_separator(arg) |
| 381 |
elif arg is None and sep == '': |
| 382 |
pair = self.word_iter.read() |
| 383 |
if len(pair[0]) != 1: |
| 384 |
raise Exception("Invalid use of " + word) |
| 385 |
else: |
| 386 |
self.print_irrelevant_word(pair) |
| 387 |
self.verb_char = pair[0] |
| 388 |
self.word_iter.add_separator(pair[0]) |
| 389 |
else: |
| 390 |
raise Exception("Invalid use of " + word) |
| 391 |
|
| 392 |
def __read_arguments(self, word): |
| 393 |
""" |
| 394 |
Loads from keywords file what arguments has got particular keyword from argument |
| 395 |
These arguments are skipped - not important for our purpose |
| 396 |
""" |
| 397 |
params = kw.keywords_list[word] |
| 398 |
for p in params: |
| 399 |
if p == "O": |
| 400 |
pass # this case is managed by '__process_keyword' method |
| 401 |
elif p == "W": |
| 402 |
self.__obligatory_argument() |
| 403 |
elif p == "S": |
| 404 |
self.__skip_brackets("[", "]") |
| 405 |
elif p == "P": |
| 406 |
self.__skip_brackets("(", ")") |
| 407 |
elif p == "C": |
| 408 |
self.__skip_brackets("{", "}") |
| 409 |
else: # unknown specifier - no argument expected |
| 410 |
pass |
| 411 |
|
| 412 |
def __obligatory_argument(self): |
| 413 |
""" |
| 414 |
Just reads another word. In case of the end of source file Exception is thrown |
| 415 |
""" |
| 416 |
pair = self.word_iter.read() |
| 417 |
if pair is None or pair[0] == "\\bye": |
| 418 |
raise Exception("No obligatory argument found") |
| 419 |
self.print_irrelevant_word(pair) |
| 420 |
return pair |
| 421 |
|
| 422 |
def __load_curly_brackets(self): |
| 423 |
""" |
| 424 |
Loads block of source code in curly brackets |
| 425 |
""" |
| 426 |
pair = self.word_iter.read() |
| 427 |
while pair is not None and pair[0] != "}": |
| 428 |
self.__process_word(pair) |
| 429 |
pair = self.word_iter.read() |
| 430 |
if pair is None: |
| 431 |
raise Exception("No closing bracket ('}') found.") |
| 432 |
else: |
| 433 |
self.print_irrelevant_word(pair) |
| 434 |
|
| 435 |
def __skip_brackets(self, opening, closing): |
| 436 |
""" |
| 437 |
Skips block of source code in brackets opening-closing |
| 438 |
""" |
| 439 |
pair = self.word_iter.read() |
| 440 |
bracket_count = 0 |
| 441 |
while True: |
| 442 |
if pair is None: |
| 443 |
raise Exception("No closing bracket ('" + closing + "') found.") |
| 444 |
elif pair[0] == opening: |
| 445 |
bracket_count += 1 |
| 446 |
self.print_irrelevant_word(pair) |
| 447 |
elif pair[0] == closing: |
| 448 |
bracket_count -= 1 |
| 449 |
self.print_irrelevant_word(pair) |
| 450 |
if bracket_count <= 0: |
| 451 |
if pair[0] != closing: |
| 452 |
self.word_iter.push_back(pair) |
| 453 |
break |
| 454 |
elif pair[0] != opening and pair[0] != closing: |
| 455 |
self.print_irrelevant_word(pair) |
| 456 |
pair = self.word_iter.read() |
| 457 |
|
| 458 |
def __skip_commentary(self): |
| 459 |
""" |
| 460 |
Skips entire line |
| 461 |
""" |
| 462 |
pair = self.word_iter.read() |
| 463 |
while pair is not None and pair[0] != "\n": |
| 464 |
self.print_irrelevant_word(pair) |
| 465 |
pair = self.word_iter.read() |
| 466 |
self.print_irrelevant_word(pair) |