| 1 | #!/usr/bin/python -u
|
|---|
| 2 | #
|
|---|
| 3 | # imports the API description and fills up a database with
|
|---|
| 4 | # name relevance to modules, functions or web pages
|
|---|
| 5 | #
|
|---|
| 6 | # Operation needed:
|
|---|
| 7 | # =================
|
|---|
| 8 | #
|
|---|
| 9 | # install mysqld, the python wrappers for mysql and libxml2, start mysqld
|
|---|
| 10 | # Change the root passwd of mysql:
|
|---|
| 11 | # mysqladmin -u root password new_password
|
|---|
| 12 | # Create the new database xmlsoft
|
|---|
| 13 | # mysqladmin -p create xmlsoft
|
|---|
| 14 | # Create a database user 'veillard' and give him passord access
|
|---|
| 15 | # change veillard and abcde with the right user name and passwd
|
|---|
| 16 | # mysql -p
|
|---|
| 17 | # password:
|
|---|
| 18 | # mysql> GRANT ALL PRIVILEGES ON xmlsoft TO veillard@localhost
|
|---|
| 19 | # IDENTIFIED BY 'abcde' WITH GRANT OPTION;
|
|---|
| 20 | #
|
|---|
| 21 | # As the user check the access:
|
|---|
| 22 | # mysql -p xmlsoft
|
|---|
| 23 | # Enter password:
|
|---|
| 24 | # Welcome to the MySQL monitor....
|
|---|
| 25 | # mysql> use xmlsoft
|
|---|
| 26 | # Database changed
|
|---|
| 27 | # mysql> quit
|
|---|
| 28 | # Bye
|
|---|
| 29 | #
|
|---|
| 30 | # Then run the script in the doc subdir, it will create the symbols and
|
|---|
| 31 | # word tables and populate them with information extracted from
|
|---|
| 32 | # the libxml2-api.xml API description, and make them accessible read-only
|
|---|
| 33 | # by nobody@loaclhost the user expected to be Apache's one
|
|---|
| 34 | #
|
|---|
| 35 | # On the Apache configuration, make sure you have php support enabled
|
|---|
| 36 | #
|
|---|
| 37 |
|
|---|
| 38 | import MySQLdb
|
|---|
| 39 | import libxml2
|
|---|
| 40 | import sys
|
|---|
| 41 | import string
|
|---|
| 42 | import os
|
|---|
| 43 |
|
|---|
| 44 | #
|
|---|
| 45 | # We are not interested in parsing errors here
|
|---|
| 46 | #
|
|---|
| 47 | def callback(ctx, str):
|
|---|
| 48 | return
|
|---|
| 49 | libxml2.registerErrorHandler(callback, None)
|
|---|
| 50 |
|
|---|
| 51 | #
|
|---|
| 52 | # The dictionary of tables required and the SQL command needed
|
|---|
| 53 | # to create them
|
|---|
| 54 | #
|
|---|
| 55 | TABLES={
|
|---|
| 56 | "symbols" : """CREATE TABLE symbols (
|
|---|
| 57 | name varchar(255) BINARY NOT NULL,
|
|---|
| 58 | module varchar(255) BINARY NOT NULL,
|
|---|
| 59 | type varchar(25) NOT NULL,
|
|---|
| 60 | descr varchar(255),
|
|---|
| 61 | UNIQUE KEY name (name),
|
|---|
| 62 | KEY module (module))""",
|
|---|
| 63 | "words" : """CREATE TABLE words (
|
|---|
| 64 | name varchar(50) BINARY NOT NULL,
|
|---|
| 65 | symbol varchar(255) BINARY NOT NULL,
|
|---|
| 66 | relevance int,
|
|---|
| 67 | KEY name (name),
|
|---|
| 68 | KEY symbol (symbol),
|
|---|
| 69 | UNIQUE KEY ID (name, symbol))""",
|
|---|
| 70 | "wordsHTML" : """CREATE TABLE wordsHTML (
|
|---|
| 71 | name varchar(50) BINARY NOT NULL,
|
|---|
| 72 | resource varchar(255) BINARY NOT NULL,
|
|---|
| 73 | section varchar(255),
|
|---|
| 74 | id varchar(50),
|
|---|
| 75 | relevance int,
|
|---|
| 76 | KEY name (name),
|
|---|
| 77 | KEY resource (resource),
|
|---|
| 78 | UNIQUE KEY ref (name, resource))""",
|
|---|
| 79 | "wordsArchive" : """CREATE TABLE wordsArchive (
|
|---|
| 80 | name varchar(50) BINARY NOT NULL,
|
|---|
| 81 | ID int(11) NOT NULL,
|
|---|
| 82 | relevance int,
|
|---|
| 83 | KEY name (name),
|
|---|
| 84 | UNIQUE KEY ref (name, ID))""",
|
|---|
| 85 | "pages" : """CREATE TABLE pages (
|
|---|
| 86 | resource varchar(255) BINARY NOT NULL,
|
|---|
| 87 | title varchar(255) BINARY NOT NULL,
|
|---|
| 88 | UNIQUE KEY name (resource))""",
|
|---|
| 89 | "archives" : """CREATE TABLE archives (
|
|---|
| 90 | ID int(11) NOT NULL auto_increment,
|
|---|
| 91 | resource varchar(255) BINARY NOT NULL,
|
|---|
| 92 | title varchar(255) BINARY NOT NULL,
|
|---|
| 93 | UNIQUE KEY id (ID,resource(255)),
|
|---|
| 94 | INDEX (ID),
|
|---|
| 95 | INDEX (resource))""",
|
|---|
| 96 | "Queries" : """CREATE TABLE Queries (
|
|---|
| 97 | ID int(11) NOT NULL auto_increment,
|
|---|
| 98 | Value varchar(50) NOT NULL,
|
|---|
| 99 | Count int(11) NOT NULL,
|
|---|
| 100 | UNIQUE KEY id (ID,Value(35)),
|
|---|
| 101 | INDEX (ID))""",
|
|---|
| 102 | "AllQueries" : """CREATE TABLE AllQueries (
|
|---|
| 103 | ID int(11) NOT NULL auto_increment,
|
|---|
| 104 | Value varchar(50) NOT NULL,
|
|---|
| 105 | Count int(11) NOT NULL,
|
|---|
| 106 | UNIQUE KEY id (ID,Value(35)),
|
|---|
| 107 | INDEX (ID))""",
|
|---|
| 108 | }
|
|---|
| 109 |
|
|---|
| 110 | #
|
|---|
| 111 | # The XML API description file to parse
|
|---|
| 112 | #
|
|---|
| 113 | API="libxml2-api.xml"
|
|---|
| 114 | DB=None
|
|---|
| 115 |
|
|---|
| 116 | #########################################################################
|
|---|
| 117 | # #
|
|---|
| 118 | # MySQL database interfaces #
|
|---|
| 119 | # #
|
|---|
| 120 | #########################################################################
|
|---|
| 121 | def createTable(db, name):
|
|---|
| 122 | global TABLES
|
|---|
| 123 |
|
|---|
| 124 | if db == None:
|
|---|
| 125 | return -1
|
|---|
| 126 | if name == None:
|
|---|
| 127 | return -1
|
|---|
| 128 | c = db.cursor()
|
|---|
| 129 |
|
|---|
| 130 | ret = c.execute("DROP TABLE IF EXISTS %s" % (name))
|
|---|
| 131 | if ret == 1:
|
|---|
| 132 | print "Removed table %s" % (name)
|
|---|
| 133 | print "Creating table %s" % (name)
|
|---|
| 134 | try:
|
|---|
| 135 | ret = c.execute(TABLES[name])
|
|---|
| 136 | except:
|
|---|
| 137 | print "Failed to create table %s" % (name)
|
|---|
| 138 | return -1
|
|---|
| 139 | return ret
|
|---|
| 140 |
|
|---|
| 141 | def checkTables(db, verbose = 1):
|
|---|
| 142 | global TABLES
|
|---|
| 143 |
|
|---|
| 144 | if db == None:
|
|---|
| 145 | return -1
|
|---|
| 146 | c = db.cursor()
|
|---|
| 147 | nbtables = c.execute("show tables")
|
|---|
| 148 | if verbose:
|
|---|
| 149 | print "Found %d tables" % (nbtables)
|
|---|
| 150 | tables = {}
|
|---|
| 151 | i = 0
|
|---|
| 152 | while i < nbtables:
|
|---|
| 153 | l = c.fetchone()
|
|---|
| 154 | name = l[0]
|
|---|
| 155 | tables[name] = {}
|
|---|
| 156 | i = i + 1
|
|---|
| 157 |
|
|---|
| 158 | for table in TABLES.keys():
|
|---|
| 159 | if not tables.has_key(table):
|
|---|
| 160 | print "table %s missing" % (table)
|
|---|
| 161 | createTable(db, table)
|
|---|
| 162 | try:
|
|---|
| 163 | ret = c.execute("SELECT count(*) from %s" % table);
|
|---|
| 164 | row = c.fetchone()
|
|---|
| 165 | if verbose:
|
|---|
| 166 | print "Table %s contains %d records" % (table, row[0])
|
|---|
| 167 | except:
|
|---|
| 168 | print "Troubles with table %s : repairing" % (table)
|
|---|
| 169 | ret = c.execute("repair table %s" % table);
|
|---|
| 170 | print "repairing returned %d" % (ret)
|
|---|
| 171 | ret = c.execute("SELECT count(*) from %s" % table);
|
|---|
| 172 | row = c.fetchone()
|
|---|
| 173 | print "Table %s contains %d records" % (table, row[0])
|
|---|
| 174 | if verbose:
|
|---|
| 175 | print "checkTables finished"
|
|---|
| 176 |
|
|---|
| 177 | # make sure apache can access the tables read-only
|
|---|
| 178 | try:
|
|---|
| 179 | ret = c.execute("GRANT SELECT ON xmlsoft.* TO nobody@localhost")
|
|---|
| 180 | ret = c.execute("GRANT INSERT,SELECT,UPDATE ON xmlsoft.Queries TO nobody@localhost")
|
|---|
| 181 | except:
|
|---|
| 182 | pass
|
|---|
| 183 | return 0
|
|---|
| 184 |
|
|---|
| 185 | def openMySQL(db="xmlsoft", passwd=None, verbose = 1):
|
|---|
| 186 | global DB
|
|---|
| 187 |
|
|---|
| 188 | if passwd == None:
|
|---|
| 189 | try:
|
|---|
| 190 | passwd = os.environ["MySQL_PASS"]
|
|---|
| 191 | except:
|
|---|
| 192 | print "No password available, set environment MySQL_PASS"
|
|---|
| 193 | sys.exit(1)
|
|---|
| 194 |
|
|---|
| 195 | DB = MySQLdb.connect(passwd=passwd, db=db)
|
|---|
| 196 | if DB == None:
|
|---|
| 197 | return -1
|
|---|
| 198 | ret = checkTables(DB, verbose)
|
|---|
| 199 | return ret
|
|---|
| 200 |
|
|---|
| 201 | def updateWord(name, symbol, relevance):
|
|---|
| 202 | global DB
|
|---|
| 203 |
|
|---|
| 204 | if DB == None:
|
|---|
| 205 | openMySQL()
|
|---|
| 206 | if DB == None:
|
|---|
| 207 | return -1
|
|---|
| 208 | if name == None:
|
|---|
| 209 | return -1
|
|---|
| 210 | if symbol == None:
|
|---|
| 211 | return -1
|
|---|
| 212 |
|
|---|
| 213 | c = DB.cursor()
|
|---|
| 214 | try:
|
|---|
| 215 | ret = c.execute(
|
|---|
| 216 | """INSERT INTO words (name, symbol, relevance) VALUES ('%s','%s', %d)""" %
|
|---|
| 217 | (name, symbol, relevance))
|
|---|
| 218 | except:
|
|---|
| 219 | try:
|
|---|
| 220 | ret = c.execute(
|
|---|
| 221 | """UPDATE words SET relevance = %d where name = '%s' and symbol = '%s'""" %
|
|---|
| 222 | (relevance, name, symbol))
|
|---|
| 223 | except:
|
|---|
| 224 | print "Update word (%s, %s, %s) failed command" % (name, symbol, relevance)
|
|---|
| 225 | print "UPDATE words SET relevance = %d where name = '%s' and symbol = '%s'" % (relevance, name, symbol)
|
|---|
| 226 | print sys.exc_type, sys.exc_value
|
|---|
| 227 | return -1
|
|---|
| 228 |
|
|---|
| 229 | return ret
|
|---|
| 230 |
|
|---|
| 231 | def updateSymbol(name, module, type, desc):
|
|---|
| 232 | global DB
|
|---|
| 233 |
|
|---|
| 234 | updateWord(name, name, 50)
|
|---|
| 235 | if DB == None:
|
|---|
| 236 | openMySQL()
|
|---|
| 237 | if DB == None:
|
|---|
| 238 | return -1
|
|---|
| 239 | if name == None:
|
|---|
| 240 | return -1
|
|---|
| 241 | if module == None:
|
|---|
| 242 | return -1
|
|---|
| 243 | if type == None:
|
|---|
| 244 | return -1
|
|---|
| 245 |
|
|---|
| 246 | try:
|
|---|
| 247 | desc = string.replace(desc, "'", " ")
|
|---|
| 248 | l = string.split(desc, ".")
|
|---|
| 249 | desc = l[0]
|
|---|
| 250 | desc = desc[0:99]
|
|---|
| 251 | except:
|
|---|
| 252 | desc = ""
|
|---|
| 253 |
|
|---|
| 254 | c = DB.cursor()
|
|---|
| 255 | try:
|
|---|
| 256 | ret = c.execute(
|
|---|
| 257 | """INSERT INTO symbols (name, module, type, descr) VALUES ('%s','%s', '%s', '%s')""" %
|
|---|
| 258 | (name, module, type, desc))
|
|---|
| 259 | except:
|
|---|
| 260 | try:
|
|---|
| 261 | ret = c.execute(
|
|---|
| 262 | """UPDATE symbols SET module='%s', type='%s', descr='%s' where name='%s'""" %
|
|---|
| 263 | (module, type, desc, name))
|
|---|
| 264 | except:
|
|---|
| 265 | print "Update symbol (%s, %s, %s) failed command" % (name, module, type)
|
|---|
| 266 | print """UPDATE symbols SET module='%s', type='%s', descr='%s' where name='%s'""" % (module, type, desc, name)
|
|---|
| 267 | print sys.exc_type, sys.exc_value
|
|---|
| 268 | return -1
|
|---|
| 269 |
|
|---|
| 270 | return ret
|
|---|
| 271 |
|
|---|
| 272 | def addFunction(name, module, desc = ""):
|
|---|
| 273 | return updateSymbol(name, module, 'function', desc)
|
|---|
| 274 |
|
|---|
| 275 | def addMacro(name, module, desc = ""):
|
|---|
| 276 | return updateSymbol(name, module, 'macro', desc)
|
|---|
| 277 |
|
|---|
| 278 | def addEnum(name, module, desc = ""):
|
|---|
| 279 | return updateSymbol(name, module, 'enum', desc)
|
|---|
| 280 |
|
|---|
| 281 | def addStruct(name, module, desc = ""):
|
|---|
| 282 | return updateSymbol(name, module, 'struct', desc)
|
|---|
| 283 |
|
|---|
| 284 | def addConst(name, module, desc = ""):
|
|---|
| 285 | return updateSymbol(name, module, 'const', desc)
|
|---|
| 286 |
|
|---|
| 287 | def addType(name, module, desc = ""):
|
|---|
| 288 | return updateSymbol(name, module, 'type', desc)
|
|---|
| 289 |
|
|---|
| 290 | def addFunctype(name, module, desc = ""):
|
|---|
| 291 | return updateSymbol(name, module, 'functype', desc)
|
|---|
| 292 |
|
|---|
| 293 | def addPage(resource, title):
|
|---|
| 294 | global DB
|
|---|
| 295 |
|
|---|
| 296 | if DB == None:
|
|---|
| 297 | openMySQL()
|
|---|
| 298 | if DB == None:
|
|---|
| 299 | return -1
|
|---|
| 300 | if resource == None:
|
|---|
| 301 | return -1
|
|---|
| 302 |
|
|---|
| 303 | c = DB.cursor()
|
|---|
| 304 | try:
|
|---|
| 305 | ret = c.execute(
|
|---|
| 306 | """INSERT INTO pages (resource, title) VALUES ('%s','%s')""" %
|
|---|
| 307 | (resource, title))
|
|---|
| 308 | except:
|
|---|
| 309 | try:
|
|---|
| 310 | ret = c.execute(
|
|---|
| 311 | """UPDATE pages SET title='%s' WHERE resource='%s'""" %
|
|---|
| 312 | (title, resource))
|
|---|
| 313 | except:
|
|---|
| 314 | print "Update symbol (%s, %s, %s) failed command" % (name, module, type)
|
|---|
| 315 | print """UPDATE pages SET title='%s' WHERE resource='%s'""" % (title, resource)
|
|---|
| 316 | print sys.exc_type, sys.exc_value
|
|---|
| 317 | return -1
|
|---|
| 318 |
|
|---|
| 319 | return ret
|
|---|
| 320 |
|
|---|
| 321 | def updateWordHTML(name, resource, desc, id, relevance):
|
|---|
| 322 | global DB
|
|---|
| 323 |
|
|---|
| 324 | if DB == None:
|
|---|
| 325 | openMySQL()
|
|---|
| 326 | if DB == None:
|
|---|
| 327 | return -1
|
|---|
| 328 | if name == None:
|
|---|
| 329 | return -1
|
|---|
| 330 | if resource == None:
|
|---|
| 331 | return -1
|
|---|
| 332 | if id == None:
|
|---|
| 333 | id = ""
|
|---|
| 334 | if desc == None:
|
|---|
| 335 | desc = ""
|
|---|
| 336 | else:
|
|---|
| 337 | try:
|
|---|
| 338 | desc = string.replace(desc, "'", " ")
|
|---|
| 339 | desc = desc[0:99]
|
|---|
| 340 | except:
|
|---|
| 341 | desc = ""
|
|---|
| 342 |
|
|---|
| 343 | c = DB.cursor()
|
|---|
| 344 | try:
|
|---|
| 345 | ret = c.execute(
|
|---|
| 346 | """INSERT INTO wordsHTML (name, resource, section, id, relevance) VALUES ('%s','%s', '%s', '%s', '%d')""" %
|
|---|
| 347 | (name, resource, desc, id, relevance))
|
|---|
| 348 | except:
|
|---|
| 349 | try:
|
|---|
| 350 | ret = c.execute(
|
|---|
| 351 | """UPDATE wordsHTML SET section='%s', id='%s', relevance='%d' where name='%s' and resource='%s'""" %
|
|---|
| 352 | (desc, id, relevance, name, resource))
|
|---|
| 353 | except:
|
|---|
| 354 | print "Update symbol (%s, %s, %d) failed command" % (name, resource, relevance)
|
|---|
| 355 | print """UPDATE wordsHTML SET section='%s', id='%s', relevance='%d' where name='%s' and resource='%s'""" % (desc, id, relevance, name, resource)
|
|---|
| 356 | print sys.exc_type, sys.exc_value
|
|---|
| 357 | return -1
|
|---|
| 358 |
|
|---|
| 359 | return ret
|
|---|
| 360 |
|
|---|
| 361 | def checkXMLMsgArchive(url):
|
|---|
| 362 | global DB
|
|---|
| 363 |
|
|---|
| 364 | if DB == None:
|
|---|
| 365 | openMySQL()
|
|---|
| 366 | if DB == None:
|
|---|
| 367 | return -1
|
|---|
| 368 | if url == None:
|
|---|
| 369 | return -1
|
|---|
| 370 |
|
|---|
| 371 | c = DB.cursor()
|
|---|
| 372 | try:
|
|---|
| 373 | ret = c.execute(
|
|---|
| 374 | """SELECT ID FROM archives WHERE resource='%s'""" % (url))
|
|---|
| 375 | row = c.fetchone()
|
|---|
| 376 | if row == None:
|
|---|
| 377 | return -1
|
|---|
| 378 | except:
|
|---|
| 379 | return -1
|
|---|
| 380 |
|
|---|
| 381 | return row[0]
|
|---|
| 382 |
|
|---|
| 383 | def addXMLMsgArchive(url, title):
|
|---|
| 384 | global DB
|
|---|
| 385 |
|
|---|
| 386 | if DB == None:
|
|---|
| 387 | openMySQL()
|
|---|
| 388 | if DB == None:
|
|---|
| 389 | return -1
|
|---|
| 390 | if url == None:
|
|---|
| 391 | return -1
|
|---|
| 392 | if title == None:
|
|---|
| 393 | title = ""
|
|---|
| 394 | else:
|
|---|
| 395 | title = string.replace(title, "'", " ")
|
|---|
| 396 | title = title[0:99]
|
|---|
| 397 |
|
|---|
| 398 | c = DB.cursor()
|
|---|
| 399 | try:
|
|---|
| 400 | cmd = """INSERT INTO archives (resource, title) VALUES ('%s','%s')""" % (url, title)
|
|---|
| 401 | ret = c.execute(cmd)
|
|---|
| 402 | cmd = """SELECT ID FROM archives WHERE resource='%s'""" % (url)
|
|---|
| 403 | ret = c.execute(cmd)
|
|---|
| 404 | row = c.fetchone()
|
|---|
| 405 | if row == None:
|
|---|
| 406 | print "addXMLMsgArchive failed to get the ID: %s" % (url)
|
|---|
| 407 | return -1
|
|---|
| 408 | except:
|
|---|
| 409 | print "addXMLMsgArchive failed command: %s" % (cmd)
|
|---|
| 410 | return -1
|
|---|
| 411 |
|
|---|
| 412 | return((int)(row[0]))
|
|---|
| 413 |
|
|---|
| 414 | def updateWordArchive(name, id, relevance):
|
|---|
| 415 | global DB
|
|---|
| 416 |
|
|---|
| 417 | if DB == None:
|
|---|
| 418 | openMySQL()
|
|---|
| 419 | if DB == None:
|
|---|
| 420 | return -1
|
|---|
| 421 | if name == None:
|
|---|
| 422 | return -1
|
|---|
| 423 | if id == None:
|
|---|
| 424 | return -1
|
|---|
| 425 |
|
|---|
| 426 | c = DB.cursor()
|
|---|
| 427 | try:
|
|---|
| 428 | ret = c.execute(
|
|---|
| 429 | """INSERT INTO wordsArchive (name, id, relevance) VALUES ('%s', '%d', '%d')""" %
|
|---|
| 430 | (name, id, relevance))
|
|---|
| 431 | except:
|
|---|
| 432 | try:
|
|---|
| 433 | ret = c.execute(
|
|---|
| 434 | """UPDATE wordsArchive SET relevance='%d' where name='%s' and ID='%d'""" %
|
|---|
| 435 | (relevance, name, id))
|
|---|
| 436 | except:
|
|---|
| 437 | print "Update word archive (%s, %d, %d) failed command" % (name, id, relevance)
|
|---|
| 438 | print """UPDATE wordsArchive SET relevance='%d' where name='%s' and ID='%d'""" % (relevance, name, id)
|
|---|
| 439 | print sys.exc_type, sys.exc_value
|
|---|
| 440 | return -1
|
|---|
| 441 |
|
|---|
| 442 | return ret
|
|---|
| 443 |
|
|---|
| 444 | #########################################################################
|
|---|
| 445 | # #
|
|---|
| 446 | # Word dictionary and analysis routines #
|
|---|
| 447 | # #
|
|---|
| 448 | #########################################################################
|
|---|
| 449 |
|
|---|
| 450 | #
|
|---|
| 451 | # top 100 english word without the one len < 3 + own set
|
|---|
| 452 | #
|
|---|
| 453 | dropWords = {
|
|---|
| 454 | 'the':0, 'this':0, 'can':0, 'man':0, 'had':0, 'him':0, 'only':0,
|
|---|
| 455 | 'and':0, 'not':0, 'been':0, 'other':0, 'even':0, 'are':0, 'was':0,
|
|---|
| 456 | 'new':0, 'most':0, 'but':0, 'when':0, 'some':0, 'made':0, 'from':0,
|
|---|
| 457 | 'who':0, 'could':0, 'after':0, 'that':0, 'will':0, 'time':0, 'also':0,
|
|---|
| 458 | 'have':0, 'more':0, 'these':0, 'did':0, 'was':0, 'two':0, 'many':0,
|
|---|
| 459 | 'they':0, 'may':0, 'before':0, 'for':0, 'which':0, 'out':0, 'then':0,
|
|---|
| 460 | 'must':0, 'one':0, 'through':0, 'with':0, 'you':0, 'said':0,
|
|---|
| 461 | 'first':0, 'back':0, 'were':0, 'what':0, 'any':0, 'years':0, 'his':0,
|
|---|
| 462 | 'her':0, 'where':0, 'all':0, 'its':0, 'now':0, 'much':0, 'she':0,
|
|---|
| 463 | 'about':0, 'such':0, 'your':0, 'there':0, 'into':0, 'like':0, 'may':0,
|
|---|
| 464 | 'would':0, 'than':0, 'our':0, 'well':0, 'their':0, 'them':0, 'over':0,
|
|---|
| 465 | 'down':0,
|
|---|
| 466 | 'net':0, 'www':0, 'bad':0, 'Okay':0, 'bin':0, 'cur':0,
|
|---|
| 467 | }
|
|---|
| 468 |
|
|---|
| 469 | wordsDict = {}
|
|---|
| 470 | wordsDictHTML = {}
|
|---|
| 471 | wordsDictArchive = {}
|
|---|
| 472 |
|
|---|
| 473 | def cleanupWordsString(str):
|
|---|
| 474 | str = string.replace(str, ".", " ")
|
|---|
| 475 | str = string.replace(str, "!", " ")
|
|---|
| 476 | str = string.replace(str, "?", " ")
|
|---|
| 477 | str = string.replace(str, ",", " ")
|
|---|
| 478 | str = string.replace(str, "'", " ")
|
|---|
| 479 | str = string.replace(str, '"', " ")
|
|---|
| 480 | str = string.replace(str, ";", " ")
|
|---|
| 481 | str = string.replace(str, "(", " ")
|
|---|
| 482 | str = string.replace(str, ")", " ")
|
|---|
| 483 | str = string.replace(str, "{", " ")
|
|---|
| 484 | str = string.replace(str, "}", " ")
|
|---|
| 485 | str = string.replace(str, "<", " ")
|
|---|
| 486 | str = string.replace(str, ">", " ")
|
|---|
| 487 | str = string.replace(str, "=", " ")
|
|---|
| 488 | str = string.replace(str, "/", " ")
|
|---|
| 489 | str = string.replace(str, "*", " ")
|
|---|
| 490 | str = string.replace(str, ":", " ")
|
|---|
| 491 | str = string.replace(str, "#", " ")
|
|---|
| 492 | str = string.replace(str, "\\", " ")
|
|---|
| 493 | str = string.replace(str, "\n", " ")
|
|---|
| 494 | str = string.replace(str, "\r", " ")
|
|---|
| 495 | str = string.replace(str, "\xc2", " ")
|
|---|
| 496 | str = string.replace(str, "\xa0", " ")
|
|---|
| 497 | return str
|
|---|
| 498 |
|
|---|
| 499 | def cleanupDescrString(str):
|
|---|
| 500 | str = string.replace(str, "'", " ")
|
|---|
| 501 | str = string.replace(str, "\n", " ")
|
|---|
| 502 | str = string.replace(str, "\r", " ")
|
|---|
| 503 | str = string.replace(str, "\xc2", " ")
|
|---|
| 504 | str = string.replace(str, "\xa0", " ")
|
|---|
| 505 | l = string.split(str)
|
|---|
| 506 | str = string.join(str)
|
|---|
| 507 | return str
|
|---|
| 508 |
|
|---|
| 509 | def splitIdentifier(str):
|
|---|
| 510 | ret = []
|
|---|
| 511 | while str != "":
|
|---|
| 512 | cur = string.lower(str[0])
|
|---|
| 513 | str = str[1:]
|
|---|
| 514 | if ((cur < 'a') or (cur > 'z')):
|
|---|
| 515 | continue
|
|---|
| 516 | while (str != "") and (str[0] >= 'A') and (str[0] <= 'Z'):
|
|---|
| 517 | cur = cur + string.lower(str[0])
|
|---|
| 518 | str = str[1:]
|
|---|
| 519 | while (str != "") and (str[0] >= 'a') and (str[0] <= 'z'):
|
|---|
| 520 | cur = cur + str[0]
|
|---|
| 521 | str = str[1:]
|
|---|
| 522 | while (str != "") and (str[0] >= '0') and (str[0] <= '9'):
|
|---|
| 523 | str = str[1:]
|
|---|
| 524 | ret.append(cur)
|
|---|
| 525 | return ret
|
|---|
| 526 |
|
|---|
| 527 | def addWord(word, module, symbol, relevance):
|
|---|
| 528 | global wordsDict
|
|---|
| 529 |
|
|---|
| 530 | if word == None or len(word) < 3:
|
|---|
| 531 | return -1
|
|---|
| 532 | if module == None or symbol == None:
|
|---|
| 533 | return -1
|
|---|
| 534 | if dropWords.has_key(word):
|
|---|
| 535 | return 0
|
|---|
| 536 | if ord(word[0]) > 0x80:
|
|---|
| 537 | return 0
|
|---|
| 538 |
|
|---|
| 539 | if wordsDict.has_key(word):
|
|---|
| 540 | d = wordsDict[word]
|
|---|
| 541 | if d == None:
|
|---|
| 542 | return 0
|
|---|
| 543 | if len(d) > 500:
|
|---|
| 544 | wordsDict[word] = None
|
|---|
| 545 | return 0
|
|---|
| 546 | try:
|
|---|
| 547 | relevance = relevance + d[(module, symbol)]
|
|---|
| 548 | except:
|
|---|
| 549 | pass
|
|---|
| 550 | else:
|
|---|
| 551 | wordsDict[word] = {}
|
|---|
| 552 | wordsDict[word][(module, symbol)] = relevance
|
|---|
| 553 | return relevance
|
|---|
| 554 |
|
|---|
| 555 | def addString(str, module, symbol, relevance):
|
|---|
| 556 | if str == None or len(str) < 3:
|
|---|
| 557 | return -1
|
|---|
| 558 | ret = 0
|
|---|
| 559 | str = cleanupWordsString(str)
|
|---|
| 560 | l = string.split(str)
|
|---|
| 561 | for word in l:
|
|---|
| 562 | if len(word) > 2:
|
|---|
| 563 | ret = ret + addWord(word, module, symbol, 5)
|
|---|
| 564 |
|
|---|
| 565 | return ret
|
|---|
| 566 |
|
|---|
| 567 | def addWordHTML(word, resource, id, section, relevance):
|
|---|
| 568 | global wordsDictHTML
|
|---|
| 569 |
|
|---|
| 570 | if word == None or len(word) < 3:
|
|---|
| 571 | return -1
|
|---|
| 572 | if resource == None or section == None:
|
|---|
| 573 | return -1
|
|---|
| 574 | if dropWords.has_key(word):
|
|---|
| 575 | return 0
|
|---|
| 576 | if ord(word[0]) > 0x80:
|
|---|
| 577 | return 0
|
|---|
| 578 |
|
|---|
| 579 | section = cleanupDescrString(section)
|
|---|
| 580 |
|
|---|
| 581 | if wordsDictHTML.has_key(word):
|
|---|
| 582 | d = wordsDictHTML[word]
|
|---|
| 583 | if d == None:
|
|---|
| 584 | print "skipped %s" % (word)
|
|---|
| 585 | return 0
|
|---|
| 586 | try:
|
|---|
| 587 | (r,i,s) = d[resource]
|
|---|
| 588 | if i != None:
|
|---|
| 589 | id = i
|
|---|
| 590 | if s != None:
|
|---|
| 591 | section = s
|
|---|
| 592 | relevance = relevance + r
|
|---|
| 593 | except:
|
|---|
| 594 | pass
|
|---|
| 595 | else:
|
|---|
| 596 | wordsDictHTML[word] = {}
|
|---|
| 597 | d = wordsDictHTML[word];
|
|---|
| 598 | d[resource] = (relevance, id, section)
|
|---|
| 599 | return relevance
|
|---|
| 600 |
|
|---|
| 601 | def addStringHTML(str, resource, id, section, relevance):
|
|---|
| 602 | if str == None or len(str) < 3:
|
|---|
| 603 | return -1
|
|---|
| 604 | ret = 0
|
|---|
| 605 | str = cleanupWordsString(str)
|
|---|
| 606 | l = string.split(str)
|
|---|
| 607 | for word in l:
|
|---|
| 608 | if len(word) > 2:
|
|---|
| 609 | try:
|
|---|
| 610 | r = addWordHTML(word, resource, id, section, relevance)
|
|---|
| 611 | if r < 0:
|
|---|
| 612 | print "addWordHTML failed: %s %s" % (word, resource)
|
|---|
| 613 | ret = ret + r
|
|---|
| 614 | except:
|
|---|
| 615 | print "addWordHTML failed: %s %s %d" % (word, resource, relevance)
|
|---|
| 616 | print sys.exc_type, sys.exc_value
|
|---|
| 617 |
|
|---|
| 618 | return ret
|
|---|
| 619 |
|
|---|
| 620 | def addWordArchive(word, id, relevance):
|
|---|
| 621 | global wordsDictArchive
|
|---|
| 622 |
|
|---|
| 623 | if word == None or len(word) < 3:
|
|---|
| 624 | return -1
|
|---|
| 625 | if id == None or id == -1:
|
|---|
| 626 | return -1
|
|---|
| 627 | if dropWords.has_key(word):
|
|---|
| 628 | return 0
|
|---|
| 629 | if ord(word[0]) > 0x80:
|
|---|
| 630 | return 0
|
|---|
| 631 |
|
|---|
| 632 | if wordsDictArchive.has_key(word):
|
|---|
| 633 | d = wordsDictArchive[word]
|
|---|
| 634 | if d == None:
|
|---|
| 635 | print "skipped %s" % (word)
|
|---|
| 636 | return 0
|
|---|
| 637 | try:
|
|---|
| 638 | r = d[id]
|
|---|
| 639 | relevance = relevance + r
|
|---|
| 640 | except:
|
|---|
| 641 | pass
|
|---|
| 642 | else:
|
|---|
| 643 | wordsDictArchive[word] = {}
|
|---|
| 644 | d = wordsDictArchive[word];
|
|---|
| 645 | d[id] = relevance
|
|---|
| 646 | return relevance
|
|---|
| 647 |
|
|---|
| 648 | def addStringArchive(str, id, relevance):
|
|---|
| 649 | if str == None or len(str) < 3:
|
|---|
| 650 | return -1
|
|---|
| 651 | ret = 0
|
|---|
| 652 | str = cleanupWordsString(str)
|
|---|
| 653 | l = string.split(str)
|
|---|
| 654 | for word in l:
|
|---|
| 655 | i = len(word)
|
|---|
| 656 | if i > 2:
|
|---|
| 657 | try:
|
|---|
| 658 | r = addWordArchive(word, id, relevance)
|
|---|
| 659 | if r < 0:
|
|---|
| 660 | print "addWordArchive failed: %s %s" % (word, id)
|
|---|
| 661 | else:
|
|---|
| 662 | ret = ret + r
|
|---|
| 663 | except:
|
|---|
| 664 | print "addWordArchive failed: %s %s %d" % (word, id, relevance)
|
|---|
| 665 | print sys.exc_type, sys.exc_value
|
|---|
| 666 | return ret
|
|---|
| 667 |
|
|---|
| 668 | #########################################################################
|
|---|
| 669 | # #
|
|---|
| 670 | # XML API description analysis #
|
|---|
| 671 | # #
|
|---|
| 672 | #########################################################################
|
|---|
| 673 |
|
|---|
| 674 | def loadAPI(filename):
|
|---|
| 675 | doc = libxml2.parseFile(filename)
|
|---|
| 676 | print "loaded %s" % (filename)
|
|---|
| 677 | return doc
|
|---|
| 678 |
|
|---|
| 679 | def foundExport(file, symbol):
|
|---|
| 680 | if file == None:
|
|---|
| 681 | return 0
|
|---|
| 682 | if symbol == None:
|
|---|
| 683 | return 0
|
|---|
| 684 | addFunction(symbol, file)
|
|---|
| 685 | l = splitIdentifier(symbol)
|
|---|
| 686 | for word in l:
|
|---|
| 687 | addWord(word, file, symbol, 10)
|
|---|
| 688 | return 1
|
|---|
| 689 |
|
|---|
| 690 | def analyzeAPIFile(top):
|
|---|
| 691 | count = 0
|
|---|
| 692 | name = top.prop("name")
|
|---|
| 693 | cur = top.children
|
|---|
| 694 | while cur != None:
|
|---|
| 695 | if cur.type == 'text':
|
|---|
| 696 | cur = cur.next
|
|---|
| 697 | continue
|
|---|
| 698 | if cur.name == "exports":
|
|---|
| 699 | count = count + foundExport(name, cur.prop("symbol"))
|
|---|
| 700 | else:
|
|---|
| 701 | print "unexpected element %s in API doc <file name='%s'>" % (name)
|
|---|
| 702 | cur = cur.next
|
|---|
| 703 | return count
|
|---|
| 704 |
|
|---|
| 705 | def analyzeAPIFiles(top):
|
|---|
| 706 | count = 0
|
|---|
| 707 | cur = top.children
|
|---|
| 708 |
|
|---|
| 709 | while cur != None:
|
|---|
| 710 | if cur.type == 'text':
|
|---|
| 711 | cur = cur.next
|
|---|
| 712 | continue
|
|---|
| 713 | if cur.name == "file":
|
|---|
| 714 | count = count + analyzeAPIFile(cur)
|
|---|
| 715 | else:
|
|---|
| 716 | print "unexpected element %s in API doc <files>" % (cur.name)
|
|---|
| 717 | cur = cur.next
|
|---|
| 718 | return count
|
|---|
| 719 |
|
|---|
| 720 | def analyzeAPIEnum(top):
|
|---|
| 721 | file = top.prop("file")
|
|---|
| 722 | if file == None:
|
|---|
| 723 | return 0
|
|---|
| 724 | symbol = top.prop("name")
|
|---|
| 725 | if symbol == None:
|
|---|
| 726 | return 0
|
|---|
| 727 |
|
|---|
| 728 | addEnum(symbol, file)
|
|---|
| 729 | l = splitIdentifier(symbol)
|
|---|
| 730 | for word in l:
|
|---|
| 731 | addWord(word, file, symbol, 10)
|
|---|
| 732 |
|
|---|
| 733 | return 1
|
|---|
| 734 |
|
|---|
| 735 | def analyzeAPIConst(top):
|
|---|
| 736 | file = top.prop("file")
|
|---|
| 737 | if file == None:
|
|---|
| 738 | return 0
|
|---|
| 739 | symbol = top.prop("name")
|
|---|
| 740 | if symbol == None:
|
|---|
| 741 | return 0
|
|---|
| 742 |
|
|---|
| 743 | addConst(symbol, file)
|
|---|
| 744 | l = splitIdentifier(symbol)
|
|---|
| 745 | for word in l:
|
|---|
| 746 | addWord(word, file, symbol, 10)
|
|---|
| 747 |
|
|---|
| 748 | return 1
|
|---|
| 749 |
|
|---|
| 750 | def analyzeAPIType(top):
|
|---|
| 751 | file = top.prop("file")
|
|---|
| 752 | if file == None:
|
|---|
| 753 | return 0
|
|---|
| 754 | symbol = top.prop("name")
|
|---|
| 755 | if symbol == None:
|
|---|
| 756 | return 0
|
|---|
| 757 |
|
|---|
| 758 | addType(symbol, file)
|
|---|
| 759 | l = splitIdentifier(symbol)
|
|---|
| 760 | for word in l:
|
|---|
| 761 | addWord(word, file, symbol, 10)
|
|---|
| 762 | return 1
|
|---|
| 763 |
|
|---|
| 764 | def analyzeAPIFunctype(top):
|
|---|
| 765 | file = top.prop("file")
|
|---|
| 766 | if file == None:
|
|---|
| 767 | return 0
|
|---|
| 768 | symbol = top.prop("name")
|
|---|
| 769 | if symbol == None:
|
|---|
| 770 | return 0
|
|---|
| 771 |
|
|---|
| 772 | addFunctype(symbol, file)
|
|---|
| 773 | l = splitIdentifier(symbol)
|
|---|
| 774 | for word in l:
|
|---|
| 775 | addWord(word, file, symbol, 10)
|
|---|
| 776 | return 1
|
|---|
| 777 |
|
|---|
| 778 | def analyzeAPIStruct(top):
|
|---|
| 779 | file = top.prop("file")
|
|---|
| 780 | if file == None:
|
|---|
| 781 | return 0
|
|---|
| 782 | symbol = top.prop("name")
|
|---|
| 783 | if symbol == None:
|
|---|
| 784 | return 0
|
|---|
| 785 |
|
|---|
| 786 | addStruct(symbol, file)
|
|---|
| 787 | l = splitIdentifier(symbol)
|
|---|
| 788 | for word in l:
|
|---|
| 789 | addWord(word, file, symbol, 10)
|
|---|
| 790 |
|
|---|
| 791 | info = top.prop("info")
|
|---|
| 792 | if info != None:
|
|---|
| 793 | info = string.replace(info, "'", " ")
|
|---|
| 794 | info = string.strip(info)
|
|---|
| 795 | l = string.split(info)
|
|---|
| 796 | for word in l:
|
|---|
| 797 | if len(word) > 2:
|
|---|
| 798 | addWord(word, file, symbol, 5)
|
|---|
| 799 | return 1
|
|---|
| 800 |
|
|---|
| 801 | def analyzeAPIMacro(top):
|
|---|
| 802 | file = top.prop("file")
|
|---|
| 803 | if file == None:
|
|---|
| 804 | return 0
|
|---|
| 805 | symbol = top.prop("name")
|
|---|
| 806 | if symbol == None:
|
|---|
| 807 | return 0
|
|---|
| 808 | symbol = string.replace(symbol, "'", " ")
|
|---|
| 809 | symbol = string.strip(symbol)
|
|---|
| 810 |
|
|---|
| 811 | info = None
|
|---|
| 812 | cur = top.children
|
|---|
| 813 | while cur != None:
|
|---|
| 814 | if cur.type == 'text':
|
|---|
| 815 | cur = cur.next
|
|---|
| 816 | continue
|
|---|
| 817 | if cur.name == "info":
|
|---|
| 818 | info = cur.content
|
|---|
| 819 | break
|
|---|
| 820 | cur = cur.next
|
|---|
| 821 |
|
|---|
| 822 | l = splitIdentifier(symbol)
|
|---|
| 823 | for word in l:
|
|---|
| 824 | addWord(word, file, symbol, 10)
|
|---|
| 825 |
|
|---|
| 826 | if info == None:
|
|---|
| 827 | addMacro(symbol, file)
|
|---|
| 828 | print "Macro %s description has no <info>" % (symbol)
|
|---|
| 829 | return 0
|
|---|
| 830 |
|
|---|
| 831 | info = string.replace(info, "'", " ")
|
|---|
| 832 | info = string.strip(info)
|
|---|
| 833 | addMacro(symbol, file, info)
|
|---|
| 834 | l = string.split(info)
|
|---|
| 835 | for word in l:
|
|---|
| 836 | if len(word) > 2:
|
|---|
| 837 | addWord(word, file, symbol, 5)
|
|---|
| 838 | return 1
|
|---|
| 839 |
|
|---|
| 840 | def analyzeAPIFunction(top):
|
|---|
| 841 | file = top.prop("file")
|
|---|
| 842 | if file == None:
|
|---|
| 843 | return 0
|
|---|
| 844 | symbol = top.prop("name")
|
|---|
| 845 | if symbol == None:
|
|---|
| 846 | return 0
|
|---|
| 847 |
|
|---|
| 848 | symbol = string.replace(symbol, "'", " ")
|
|---|
| 849 | symbol = string.strip(symbol)
|
|---|
| 850 | info = None
|
|---|
| 851 | cur = top.children
|
|---|
| 852 | while cur != None:
|
|---|
| 853 | if cur.type == 'text':
|
|---|
| 854 | cur = cur.next
|
|---|
| 855 | continue
|
|---|
| 856 | if cur.name == "info":
|
|---|
| 857 | info = cur.content
|
|---|
| 858 | elif cur.name == "return":
|
|---|
| 859 | rinfo = cur.prop("info")
|
|---|
| 860 | if rinfo != None:
|
|---|
| 861 | rinfo = string.replace(rinfo, "'", " ")
|
|---|
| 862 | rinfo = string.strip(rinfo)
|
|---|
| 863 | addString(rinfo, file, symbol, 7)
|
|---|
| 864 | elif cur.name == "arg":
|
|---|
| 865 | ainfo = cur.prop("info")
|
|---|
| 866 | if ainfo != None:
|
|---|
| 867 | ainfo = string.replace(ainfo, "'", " ")
|
|---|
| 868 | ainfo = string.strip(ainfo)
|
|---|
| 869 | addString(ainfo, file, symbol, 5)
|
|---|
| 870 | name = cur.prop("name")
|
|---|
| 871 | if name != None:
|
|---|
| 872 | name = string.replace(name, "'", " ")
|
|---|
| 873 | name = string.strip(name)
|
|---|
| 874 | addWord(name, file, symbol, 7)
|
|---|
| 875 | cur = cur.next
|
|---|
| 876 | if info == None:
|
|---|
| 877 | print "Function %s description has no <info>" % (symbol)
|
|---|
| 878 | addFunction(symbol, file, "")
|
|---|
| 879 | else:
|
|---|
| 880 | info = string.replace(info, "'", " ")
|
|---|
| 881 | info = string.strip(info)
|
|---|
| 882 | addFunction(symbol, file, info)
|
|---|
| 883 | addString(info, file, symbol, 5)
|
|---|
| 884 |
|
|---|
| 885 | l = splitIdentifier(symbol)
|
|---|
| 886 | for word in l:
|
|---|
| 887 | addWord(word, file, symbol, 10)
|
|---|
| 888 |
|
|---|
| 889 | return 1
|
|---|
| 890 |
|
|---|
| 891 | def analyzeAPISymbols(top):
|
|---|
| 892 | count = 0
|
|---|
| 893 | cur = top.children
|
|---|
| 894 |
|
|---|
| 895 | while cur != None:
|
|---|
| 896 | if cur.type == 'text':
|
|---|
| 897 | cur = cur.next
|
|---|
| 898 | continue
|
|---|
| 899 | if cur.name == "macro":
|
|---|
| 900 | count = count + analyzeAPIMacro(cur)
|
|---|
| 901 | elif cur.name == "function":
|
|---|
| 902 | count = count + analyzeAPIFunction(cur)
|
|---|
| 903 | elif cur.name == "const":
|
|---|
| 904 | count = count + analyzeAPIConst(cur)
|
|---|
| 905 | elif cur.name == "typedef":
|
|---|
| 906 | count = count + analyzeAPIType(cur)
|
|---|
| 907 | elif cur.name == "struct":
|
|---|
| 908 | count = count + analyzeAPIStruct(cur)
|
|---|
| 909 | elif cur.name == "enum":
|
|---|
| 910 | count = count + analyzeAPIEnum(cur)
|
|---|
| 911 | elif cur.name == "functype":
|
|---|
| 912 | count = count + analyzeAPIFunctype(cur)
|
|---|
| 913 | else:
|
|---|
| 914 | print "unexpected element %s in API doc <files>" % (cur.name)
|
|---|
| 915 | cur = cur.next
|
|---|
| 916 | return count
|
|---|
| 917 |
|
|---|
| 918 | def analyzeAPI(doc):
|
|---|
| 919 | count = 0
|
|---|
| 920 | if doc == None:
|
|---|
| 921 | return -1
|
|---|
| 922 | root = doc.getRootElement()
|
|---|
| 923 | if root.name != "api":
|
|---|
| 924 | print "Unexpected root name"
|
|---|
| 925 | return -1
|
|---|
| 926 | cur = root.children
|
|---|
| 927 | while cur != None:
|
|---|
| 928 | if cur.type == 'text':
|
|---|
| 929 | cur = cur.next
|
|---|
| 930 | continue
|
|---|
| 931 | if cur.name == "files":
|
|---|
| 932 | pass
|
|---|
| 933 | # count = count + analyzeAPIFiles(cur)
|
|---|
| 934 | elif cur.name == "symbols":
|
|---|
| 935 | count = count + analyzeAPISymbols(cur)
|
|---|
| 936 | else:
|
|---|
| 937 | print "unexpected element %s in API doc" % (cur.name)
|
|---|
| 938 | cur = cur.next
|
|---|
| 939 | return count
|
|---|
| 940 |
|
|---|
| 941 | #########################################################################
|
|---|
| 942 | # #
|
|---|
| 943 | # Web pages parsing and analysis #
|
|---|
| 944 | # #
|
|---|
| 945 | #########################################################################
|
|---|
| 946 |
|
|---|
| 947 | import glob
|
|---|
| 948 |
|
|---|
| 949 | def analyzeHTMLText(doc, resource, p, section, id):
|
|---|
| 950 | words = 0
|
|---|
| 951 | try:
|
|---|
| 952 | content = p.content
|
|---|
| 953 | words = words + addStringHTML(content, resource, id, section, 5)
|
|---|
| 954 | except:
|
|---|
| 955 | return -1
|
|---|
| 956 | return words
|
|---|
| 957 |
|
|---|
| 958 | def analyzeHTMLPara(doc, resource, p, section, id):
|
|---|
| 959 | words = 0
|
|---|
| 960 | try:
|
|---|
| 961 | content = p.content
|
|---|
| 962 | words = words + addStringHTML(content, resource, id, section, 5)
|
|---|
| 963 | except:
|
|---|
| 964 | return -1
|
|---|
| 965 | return words
|
|---|
| 966 |
|
|---|
| 967 | def analyzeHTMLPre(doc, resource, p, section, id):
|
|---|
| 968 | words = 0
|
|---|
| 969 | try:
|
|---|
| 970 | content = p.content
|
|---|
| 971 | words = words + addStringHTML(content, resource, id, section, 5)
|
|---|
| 972 | except:
|
|---|
| 973 | return -1
|
|---|
| 974 | return words
|
|---|
| 975 |
|
|---|
| 976 | def analyzeHTML(doc, resource, p, section, id):
|
|---|
| 977 | words = 0
|
|---|
| 978 | try:
|
|---|
| 979 | content = p.content
|
|---|
| 980 | words = words + addStringHTML(content, resource, id, section, 5)
|
|---|
| 981 | except:
|
|---|
| 982 | return -1
|
|---|
| 983 | return words
|
|---|
| 984 |
|
|---|
| 985 | def analyzeHTML(doc, resource):
|
|---|
| 986 | para = 0;
|
|---|
| 987 | ctxt = doc.xpathNewContext()
|
|---|
| 988 | try:
|
|---|
| 989 | res = ctxt.xpathEval("//head/title")
|
|---|
| 990 | title = res[0].content
|
|---|
| 991 | except:
|
|---|
| 992 | title = "Page %s" % (resource)
|
|---|
| 993 | addPage(resource, title)
|
|---|
| 994 | try:
|
|---|
| 995 | items = ctxt.xpathEval("//h1 | //h2 | //h3 | //text()")
|
|---|
| 996 | section = title
|
|---|
| 997 | id = ""
|
|---|
| 998 | for item in items:
|
|---|
| 999 | if item.name == 'h1' or item.name == 'h2' or item.name == 'h3':
|
|---|
| 1000 | section = item.content
|
|---|
| 1001 | if item.prop("id"):
|
|---|
| 1002 | id = item.prop("id")
|
|---|
| 1003 | elif item.prop("name"):
|
|---|
| 1004 | id = item.prop("name")
|
|---|
| 1005 | elif item.type == 'text':
|
|---|
| 1006 | analyzeHTMLText(doc, resource, item, section, id)
|
|---|
| 1007 | para = para + 1
|
|---|
| 1008 | elif item.name == 'p':
|
|---|
| 1009 | analyzeHTMLPara(doc, resource, item, section, id)
|
|---|
| 1010 | para = para + 1
|
|---|
| 1011 | elif item.name == 'pre':
|
|---|
| 1012 | analyzeHTMLPre(doc, resource, item, section, id)
|
|---|
| 1013 | para = para + 1
|
|---|
| 1014 | else:
|
|---|
| 1015 | print "Page %s, unexpected %s element" % (resource, item.name)
|
|---|
| 1016 | except:
|
|---|
| 1017 | print "Page %s: problem analyzing" % (resource)
|
|---|
| 1018 | print sys.exc_type, sys.exc_value
|
|---|
| 1019 |
|
|---|
| 1020 | return para
|
|---|
| 1021 |
|
|---|
| 1022 | def analyzeHTMLPages():
|
|---|
| 1023 | ret = 0
|
|---|
| 1024 | HTMLfiles = glob.glob("*.html") + glob.glob("tutorial/*.html")
|
|---|
| 1025 | for html in HTMLfiles:
|
|---|
| 1026 | if html[0:3] == "API":
|
|---|
| 1027 | continue
|
|---|
| 1028 | if html == "xml.html":
|
|---|
| 1029 | continue
|
|---|
| 1030 | try:
|
|---|
| 1031 | doc = libxml2.parseFile(html)
|
|---|
| 1032 | except:
|
|---|
| 1033 | doc = libxml2.htmlParseFile(html, None)
|
|---|
| 1034 | try:
|
|---|
| 1035 | res = analyzeHTML(doc, html)
|
|---|
| 1036 | print "Parsed %s : %d paragraphs" % (html, res)
|
|---|
| 1037 | ret = ret + 1
|
|---|
| 1038 | except:
|
|---|
| 1039 | print "could not parse %s" % (html)
|
|---|
| 1040 | return ret
|
|---|
| 1041 |
|
|---|
| 1042 | #########################################################################
|
|---|
| 1043 | # #
|
|---|
| 1044 | # Mail archives parsing and analysis #
|
|---|
| 1045 | # #
|
|---|
| 1046 | #########################################################################
|
|---|
| 1047 |
|
|---|
| 1048 | import time
|
|---|
| 1049 |
|
|---|
| 1050 | def getXMLDateArchive(t = None):
|
|---|
| 1051 | if t == None:
|
|---|
| 1052 | t = time.time()
|
|---|
| 1053 | T = time.gmtime(t)
|
|---|
| 1054 | month = time.strftime("%B", T)
|
|---|
| 1055 | year = T[0]
|
|---|
| 1056 | url = "http://mail.gnome.org/archives/xml/%d-%s/date.html" % (year, month)
|
|---|
| 1057 | return url
|
|---|
| 1058 |
|
|---|
| 1059 | def scanXMLMsgArchive(url, title, force = 0):
|
|---|
| 1060 | if url == None or title == None:
|
|---|
| 1061 | return 0
|
|---|
| 1062 |
|
|---|
| 1063 | ID = checkXMLMsgArchive(url)
|
|---|
| 1064 | if force == 0 and ID != -1:
|
|---|
| 1065 | return 0
|
|---|
| 1066 |
|
|---|
| 1067 | if ID == -1:
|
|---|
| 1068 | ID = addXMLMsgArchive(url, title)
|
|---|
| 1069 | if ID == -1:
|
|---|
| 1070 | return 0
|
|---|
| 1071 |
|
|---|
| 1072 | try:
|
|---|
| 1073 | print "Loading %s" % (url)
|
|---|
| 1074 | doc = libxml2.htmlParseFile(url, None);
|
|---|
| 1075 | except:
|
|---|
| 1076 | doc = None
|
|---|
| 1077 | if doc == None:
|
|---|
| 1078 | print "Failed to parse %s" % (url)
|
|---|
| 1079 | return 0
|
|---|
| 1080 |
|
|---|
| 1081 | addStringArchive(title, ID, 20)
|
|---|
| 1082 | ctxt = doc.xpathNewContext()
|
|---|
| 1083 | texts = ctxt.xpathEval("//pre//text()")
|
|---|
| 1084 | for text in texts:
|
|---|
| 1085 | addStringArchive(text.content, ID, 5)
|
|---|
| 1086 |
|
|---|
| 1087 | return 1
|
|---|
| 1088 |
|
|---|
| 1089 | def scanXMLDateArchive(t = None, force = 0):
|
|---|
| 1090 | global wordsDictArchive
|
|---|
| 1091 |
|
|---|
| 1092 | wordsDictArchive = {}
|
|---|
| 1093 |
|
|---|
| 1094 | url = getXMLDateArchive(t)
|
|---|
| 1095 | print "loading %s" % (url)
|
|---|
| 1096 | try:
|
|---|
| 1097 | doc = libxml2.htmlParseFile(url, None);
|
|---|
| 1098 | except:
|
|---|
| 1099 | doc = None
|
|---|
| 1100 | if doc == None:
|
|---|
| 1101 | print "Failed to parse %s" % (url)
|
|---|
| 1102 | return -1
|
|---|
| 1103 | ctxt = doc.xpathNewContext()
|
|---|
| 1104 | anchors = ctxt.xpathEval("//a[@href]")
|
|---|
| 1105 | links = 0
|
|---|
| 1106 | newmsg = 0
|
|---|
| 1107 | for anchor in anchors:
|
|---|
| 1108 | href = anchor.prop("href")
|
|---|
| 1109 | if href == None or href[0:3] != "msg":
|
|---|
| 1110 | continue
|
|---|
| 1111 | try:
|
|---|
| 1112 | links = links + 1
|
|---|
| 1113 |
|
|---|
| 1114 | msg = libxml2.buildURI(href, url)
|
|---|
| 1115 | title = anchor.content
|
|---|
| 1116 | if title != None and title[0:4] == 'Re: ':
|
|---|
| 1117 | title = title[4:]
|
|---|
| 1118 | if title != None and title[0:6] == '[xml] ':
|
|---|
| 1119 | title = title[6:]
|
|---|
| 1120 | newmsg = newmsg + scanXMLMsgArchive(msg, title, force)
|
|---|
| 1121 |
|
|---|
| 1122 | except:
|
|---|
| 1123 | pass
|
|---|
| 1124 |
|
|---|
| 1125 | return newmsg
|
|---|
| 1126 |
|
|---|
| 1127 |
|
|---|
| 1128 | #########################################################################
|
|---|
| 1129 | # #
|
|---|
| 1130 | # Main code: open the DB, the API XML and analyze it #
|
|---|
| 1131 | # #
|
|---|
| 1132 | #########################################################################
|
|---|
| 1133 | def analyzeArchives(t = None, force = 0):
|
|---|
| 1134 | global wordsDictArchive
|
|---|
| 1135 |
|
|---|
| 1136 | ret = scanXMLDateArchive(t, force)
|
|---|
| 1137 | print "Indexed %d words in %d archive pages" % (len(wordsDictArchive), ret)
|
|---|
| 1138 |
|
|---|
| 1139 | i = 0
|
|---|
| 1140 | skipped = 0
|
|---|
| 1141 | for word in wordsDictArchive.keys():
|
|---|
| 1142 | refs = wordsDictArchive[word]
|
|---|
| 1143 | if refs == None:
|
|---|
| 1144 | skipped = skipped + 1
|
|---|
| 1145 | continue;
|
|---|
| 1146 | for id in refs.keys():
|
|---|
| 1147 | relevance = refs[id]
|
|---|
| 1148 | updateWordArchive(word, id, relevance)
|
|---|
| 1149 | i = i + 1
|
|---|
| 1150 |
|
|---|
| 1151 | print "Found %d associations in HTML pages" % (i)
|
|---|
| 1152 |
|
|---|
| 1153 | def analyzeHTMLTop():
|
|---|
| 1154 | global wordsDictHTML
|
|---|
| 1155 |
|
|---|
| 1156 | ret = analyzeHTMLPages()
|
|---|
| 1157 | print "Indexed %d words in %d HTML pages" % (len(wordsDictHTML), ret)
|
|---|
| 1158 |
|
|---|
| 1159 | i = 0
|
|---|
| 1160 | skipped = 0
|
|---|
| 1161 | for word in wordsDictHTML.keys():
|
|---|
| 1162 | refs = wordsDictHTML[word]
|
|---|
| 1163 | if refs == None:
|
|---|
| 1164 | skipped = skipped + 1
|
|---|
| 1165 | continue;
|
|---|
| 1166 | for resource in refs.keys():
|
|---|
| 1167 | (relevance, id, section) = refs[resource]
|
|---|
| 1168 | updateWordHTML(word, resource, section, id, relevance)
|
|---|
| 1169 | i = i + 1
|
|---|
| 1170 |
|
|---|
| 1171 | print "Found %d associations in HTML pages" % (i)
|
|---|
| 1172 |
|
|---|
| 1173 | def analyzeAPITop():
|
|---|
| 1174 | global wordsDict
|
|---|
| 1175 | global API
|
|---|
| 1176 |
|
|---|
| 1177 | try:
|
|---|
| 1178 | doc = loadAPI(API)
|
|---|
| 1179 | ret = analyzeAPI(doc)
|
|---|
| 1180 | print "Analyzed %d blocks" % (ret)
|
|---|
| 1181 | doc.freeDoc()
|
|---|
| 1182 | except:
|
|---|
| 1183 | print "Failed to parse and analyze %s" % (API)
|
|---|
| 1184 | print sys.exc_type, sys.exc_value
|
|---|
| 1185 | sys.exit(1)
|
|---|
| 1186 |
|
|---|
| 1187 | print "Indexed %d words" % (len(wordsDict))
|
|---|
| 1188 | i = 0
|
|---|
| 1189 | skipped = 0
|
|---|
| 1190 | for word in wordsDict.keys():
|
|---|
| 1191 | refs = wordsDict[word]
|
|---|
| 1192 | if refs == None:
|
|---|
| 1193 | skipped = skipped + 1
|
|---|
| 1194 | continue;
|
|---|
| 1195 | for (module, symbol) in refs.keys():
|
|---|
| 1196 | updateWord(word, symbol, refs[(module, symbol)])
|
|---|
| 1197 | i = i + 1
|
|---|
| 1198 |
|
|---|
| 1199 | print "Found %d associations, skipped %d words" % (i, skipped)
|
|---|
| 1200 |
|
|---|
| 1201 | def usage():
|
|---|
| 1202 | print "Usage index.py [--force] [--archive] [--archive-year year] [--archive-month month] [--API] [--docs]"
|
|---|
| 1203 | sys.exit(1)
|
|---|
| 1204 |
|
|---|
| 1205 | def main():
|
|---|
| 1206 | try:
|
|---|
| 1207 | openMySQL()
|
|---|
| 1208 | except:
|
|---|
| 1209 | print "Failed to open the database"
|
|---|
| 1210 | print sys.exc_type, sys.exc_value
|
|---|
| 1211 | sys.exit(1)
|
|---|
| 1212 |
|
|---|
| 1213 | args = sys.argv[1:]
|
|---|
| 1214 | force = 0
|
|---|
| 1215 | if args:
|
|---|
| 1216 | i = 0
|
|---|
| 1217 | while i < len(args):
|
|---|
| 1218 | if args[i] == '--force':
|
|---|
| 1219 | force = 1
|
|---|
| 1220 | elif args[i] == '--archive':
|
|---|
| 1221 | analyzeArchives(None, force)
|
|---|
| 1222 | elif args[i] == '--archive-year':
|
|---|
| 1223 | i = i + 1;
|
|---|
| 1224 | year = args[i]
|
|---|
| 1225 | months = ["January" , "February", "March", "April", "May",
|
|---|
| 1226 | "June", "July", "August", "September", "October",
|
|---|
| 1227 | "November", "December"];
|
|---|
| 1228 | for month in months:
|
|---|
| 1229 | try:
|
|---|
| 1230 | str = "%s-%s" % (year, month)
|
|---|
| 1231 | T = time.strptime(str, "%Y-%B")
|
|---|
| 1232 | t = time.mktime(T) + 3600 * 24 * 10;
|
|---|
| 1233 | analyzeArchives(t, force)
|
|---|
| 1234 | except:
|
|---|
| 1235 | print "Failed to index month archive:"
|
|---|
| 1236 | print sys.exc_type, sys.exc_value
|
|---|
| 1237 | elif args[i] == '--archive-month':
|
|---|
| 1238 | i = i + 1;
|
|---|
| 1239 | month = args[i]
|
|---|
| 1240 | try:
|
|---|
| 1241 | T = time.strptime(month, "%Y-%B")
|
|---|
| 1242 | t = time.mktime(T) + 3600 * 24 * 10;
|
|---|
| 1243 | analyzeArchives(t, force)
|
|---|
| 1244 | except:
|
|---|
| 1245 | print "Failed to index month archive:"
|
|---|
| 1246 | print sys.exc_type, sys.exc_value
|
|---|
| 1247 | elif args[i] == '--API':
|
|---|
| 1248 | analyzeAPITop()
|
|---|
| 1249 | elif args[i] == '--docs':
|
|---|
| 1250 | analyzeHTMLTop()
|
|---|
| 1251 | else:
|
|---|
| 1252 | usage()
|
|---|
| 1253 | i = i + 1
|
|---|
| 1254 | else:
|
|---|
| 1255 | usage()
|
|---|
| 1256 |
|
|---|
| 1257 | if __name__ == "__main__":
|
|---|
| 1258 | main()
|
|---|
