index.py 32.1 KB
Newer Older
1 2 3 4 5
#!/usr/bin/python -u
#
# imports the API description and fills up a database with
# name relevance to modules, functions or web pages
#
6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
# Operation needed:
# =================
#
# install mysqld, the python wrappers for mysql and libxml2, start mysqld
# Change the root passwd of mysql:
#    mysqladmin -u root password new_password
# Create the new database xmlsoft
#    mysqladmin -p create xmlsoft
# Create a database user 'veillard' and give him passord access
# change veillard and abcde with the right user name and passwd
#    mysql -p
#    password:
#    mysql> GRANT ALL PRIVILEGES ON xmlsoft TO veillard@localhost
#           IDENTIFIED BY 'abcde' WITH GRANT OPTION;
#
# As the user check the access:
#    mysql -p xmlsoft
#    Enter password:
#    Welcome to the MySQL monitor....
#    mysql> use xmlsoft
#    Database changed
#    mysql> quit
#    Bye
#
# Then run the script in the doc subdir, it will create the symbols and
# word tables and populate them with informations extracted from 
Jared Yanovich's avatar
Jared Yanovich committed
32
# the libxml2-api.xml API description, and make them accessible read-only
33 34 35 36 37
# by nobody@loaclhost the user expected to be Apache's one
#
# On the Apache configuration, make sure you have php support enabled
#

38 39 40 41 42 43
import MySQLdb
import libxml2
import sys
import string
import os

44 45 46 47 48 49 50
#
# We are not interested in parsing errors here
#
def callback(ctx, str):
    return
libxml2.registerErrorHandler(callback, None)

51
#
52
# The dictionary of tables required and the SQL command needed
53 54 55 56
# to create them
#
TABLES={
  "symbols" : """CREATE TABLE symbols (
57 58
           name varchar(255) BINARY NOT NULL,
	   module varchar(255) BINARY NOT NULL,
59 60 61 62 63
           type varchar(25) NOT NULL,
	   descr varchar(255),
	   UNIQUE KEY name (name),
	   KEY module (module))""",
  "words" : """CREATE TABLE words (
64 65
           name varchar(50) BINARY NOT NULL,
	   symbol varchar(255) BINARY NOT NULL,
66 67 68 69
           relevance int,
	   KEY name (name),
	   KEY symbol (symbol),
	   UNIQUE KEY ID (name, symbol))""",
70
  "wordsHTML" : """CREATE TABLE wordsHTML (
71 72
           name varchar(50) BINARY NOT NULL,
	   resource varchar(255) BINARY NOT NULL,
73 74 75 76 77 78
	   section varchar(255),
	   id varchar(50),
           relevance int,
	   KEY name (name),
	   KEY resource (resource),
	   UNIQUE KEY ref (name, resource))""",
79 80 81 82 83 84
  "wordsArchive" : """CREATE TABLE wordsArchive (
           name varchar(50) BINARY NOT NULL,
	   ID int(11) NOT NULL,
           relevance int,
	   KEY name (name),
	   UNIQUE KEY ref (name, ID))""",
85
  "pages" : """CREATE TABLE pages (
86 87
           resource varchar(255) BINARY NOT NULL,
	   title varchar(255) BINARY NOT NULL,
88
	   UNIQUE KEY name (resource))""",
89 90 91 92 93 94 95
  "archives" : """CREATE TABLE archives (
           ID int(11) NOT NULL auto_increment,
           resource varchar(255) BINARY NOT NULL,
	   title varchar(255) BINARY NOT NULL,
	   UNIQUE KEY id (ID,resource(255)),
	   INDEX (ID),
	   INDEX (resource))""",
96 97 98 99 100 101
  "Queries" : """CREATE TABLE Queries (
           ID int(11) NOT NULL auto_increment,
	   Value varchar(50) NOT NULL,
	   Count int(11) NOT NULL,
	   UNIQUE KEY id (ID,Value(35)),
	   INDEX (ID))""",
102 103 104 105 106 107
  "AllQueries" : """CREATE TABLE AllQueries (
           ID int(11) NOT NULL auto_increment,
	   Value varchar(50) NOT NULL,
	   Count int(11) NOT NULL,
	   UNIQUE KEY id (ID,Value(35)),
	   INDEX (ID))""",
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
}

#
# The XML API description file to parse
#
API="libxml2-api.xml"
DB=None

#########################################################################
#									#
#                  MySQL database interfaces				#
#									#
#########################################################################
def createTable(db, name):
    global TABLES

    if db == None:
        return -1
    if name == None:
        return -1
    c = db.cursor()

    ret = c.execute("DROP TABLE IF EXISTS %s" % (name))
    if ret == 1:
        print "Removed table %s" % (name)
    print "Creating table %s" % (name)
    try:
        ret = c.execute(TABLES[name])
    except:
        print "Failed to create table %s" % (name)
	return -1
    return ret

141
def checkTables(db, verbose = 1):
142 143 144 145 146 147
    global TABLES

    if db == None:
        return -1
    c = db.cursor()
    nbtables = c.execute("show tables")
148 149
    if verbose:
	print "Found %d tables" % (nbtables)
150 151 152 153 154 155 156 157 158 159 160 161
    tables = {}
    i = 0
    while i < nbtables:
        l = c.fetchone()
	name = l[0]
	tables[name] = {}
        i = i + 1

    for table in TABLES.keys():
        if not tables.has_key(table):
	    print "table %s missing" % (table)
	    createTable(db, table)
162 163 164
	try:
	    ret = c.execute("SELECT count(*) from %s" % table);
	    row = c.fetchone()
165 166
	    if verbose:
		print "Table %s contains %d records" % (table, row[0])
167 168 169 170 171 172 173
	except:
	    print "Troubles with table %s : repairing" % (table)
	    ret = c.execute("repair table %s" % table);
	    print "repairing returned %d" % (ret)
	    ret = c.execute("SELECT count(*) from %s" % table);
	    row = c.fetchone()
	    print "Table %s contains %d records" % (table, row[0])
174 175
    if verbose:
	print "checkTables finished"
176 177 178 179

    # make sure apache can access the tables read-only
    try:
	ret = c.execute("GRANT SELECT ON xmlsoft.* TO nobody@localhost")
180
	ret = c.execute("GRANT INSERT,SELECT,UPDATE  ON xmlsoft.Queries TO nobody@localhost")
181 182 183 184
    except:
        pass
    return 0
    
185
def openMySQL(db="xmlsoft", passwd=None, verbose = 1):
186 187 188
    global DB

    if passwd == None:
189 190 191 192 193 194
        try:
	    passwd = os.environ["MySQL_PASS"]
	except:
	    print "No password available, set environment MySQL_PASS"
	    sys.exit(1)

195 196 197
    DB = MySQLdb.connect(passwd=passwd, db=db)
    if DB == None:
        return -1
198
    ret = checkTables(DB, verbose)
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
    return ret

def updateWord(name, symbol, relevance):
    global DB

    if DB == None:
        openMySQL()
    if DB == None:
        return -1
    if name == None:
        return -1
    if symbol == None:
        return -1

    c = DB.cursor()
    try:
	ret = c.execute(
"""INSERT INTO words (name, symbol, relevance) VALUES ('%s','%s', %d)""" %
		(name, symbol, relevance))
    except:
        try:
	    ret = c.execute(
    """UPDATE words SET relevance = %d where name = '%s' and symbol = '%s'""" %
		    (relevance, name, symbol))
	except:
	    print "Update word (%s, %s, %s) failed command" % (name, symbol, relevance)
	    print "UPDATE words SET relevance = %d where name = '%s' and symbol = '%s'" % (relevance, name, symbol)
	    print sys.exc_type, sys.exc_value
	    return -1
	     
    return ret

def updateSymbol(name, module, type, desc):
    global DB

    updateWord(name, name, 50)
    if DB == None:
        openMySQL()
    if DB == None:
        return -1
    if name == None:
        return -1
    if module == None:
        return -1
    if type == None:
        return -1

    try:
	desc = string.replace(desc, "'", " ")
	l = string.split(desc, ".")
	desc = l[0]
	desc = desc[0:99]
    except:
        desc = ""

    c = DB.cursor()
    try:
	ret = c.execute(
"""INSERT INTO symbols (name, module, type, descr) VALUES ('%s','%s', '%s', '%s')""" %
                    (name, module, type, desc))
    except:
        try:
	    ret = c.execute(
"""UPDATE symbols SET module='%s', type='%s', descr='%s' where name='%s'""" %
                    (module, type, desc, name))
        except:
	    print "Update symbol (%s, %s, %s) failed command" % (name, module, type)
	    print """UPDATE symbols SET module='%s', type='%s', descr='%s' where name='%s'""" % (module, type, desc, name)
	    print sys.exc_type, sys.exc_value
	    return -1
	     
    return ret
        
def addFunction(name, module, desc = ""):
    return updateSymbol(name, module, 'function', desc)

def addMacro(name, module, desc = ""):
    return updateSymbol(name, module, 'macro', desc)

def addEnum(name, module, desc = ""):
    return updateSymbol(name, module, 'enum', desc)

def addStruct(name, module, desc = ""):
    return updateSymbol(name, module, 'struct', desc)

def addConst(name, module, desc = ""):
    return updateSymbol(name, module, 'const', desc)

def addType(name, module, desc = ""):
    return updateSymbol(name, module, 'type', desc)

def addFunctype(name, module, desc = ""):
    return updateSymbol(name, module, 'functype', desc)

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
def addPage(resource, title):
    global DB

    if DB == None:
        openMySQL()
    if DB == None:
        return -1
    if resource == None:
        return -1

    c = DB.cursor()
    try:
	ret = c.execute(
	    """INSERT INTO pages (resource, title) VALUES ('%s','%s')""" %
                    (resource, title))
    except:
        try:
	    ret = c.execute(
		"""UPDATE pages SET title='%s' WHERE resource='%s'""" %
                    (title, resource))
        except:
	    print "Update symbol (%s, %s, %s) failed command" % (name, module, type)
	    print """UPDATE pages SET title='%s' WHERE resource='%s'""" % (title, resource)
	    print sys.exc_type, sys.exc_value
	    return -1
	     
    return ret

def updateWordHTML(name, resource, desc, id, relevance):
    global DB

    if DB == None:
        openMySQL()
    if DB == None:
        return -1
    if name == None:
        return -1
    if resource == None:
        return -1
    if id == None:
        id = ""
    if desc == None:
        desc = ""
    else:
	try:
	    desc = string.replace(desc, "'", " ")
	    desc = desc[0:99]
	except:
	    desc = ""

    c = DB.cursor()
    try:
	ret = c.execute(
"""INSERT INTO wordsHTML (name, resource, section, id, relevance) VALUES ('%s','%s', '%s', '%s', '%d')""" %
                    (name, resource, desc, id, relevance))
    except:
        try:
	    ret = c.execute(
"""UPDATE wordsHTML SET section='%s', id='%s', relevance='%d' where name='%s' and resource='%s'""" %
                    (desc, id, relevance, name, resource))
        except:
	    print "Update symbol (%s, %s, %d) failed command" % (name, resource, relevance)
	    print """UPDATE wordsHTML SET section='%s', id='%s', relevance='%d' where name='%s' and resource='%s'""" % (desc, id, relevance, name, resource)
	    print sys.exc_type, sys.exc_value
	    return -1
	     
    return ret
360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440

def checkXMLMsgArchive(url):
    global DB

    if DB == None:
        openMySQL()
    if DB == None:
        return -1
    if url == None:
        return -1

    c = DB.cursor()
    try:
	ret = c.execute(
	    """SELECT ID FROM archives WHERE resource='%s'""" % (url))
	row = c.fetchone()
	if row == None:
	    return -1
    except:
	return -1
	     
    return row[0]
    
def addXMLMsgArchive(url, title):
    global DB

    if DB == None:
        openMySQL()
    if DB == None:
        return -1
    if url == None:
        return -1
    if title == None:
        title = ""
    else:
	title = string.replace(title, "'", " ")
	title = title[0:99]

    c = DB.cursor()
    try:
        cmd = """INSERT INTO archives (resource, title) VALUES ('%s','%s')""" % (url, title)
        ret = c.execute(cmd)
	cmd = """SELECT ID FROM archives WHERE resource='%s'""" % (url)
        ret = c.execute(cmd)
	row = c.fetchone()
	if row == None:
	    print "addXMLMsgArchive failed to get the ID: %s" % (url)
	    return -1
    except:
        print "addXMLMsgArchive failed command: %s" % (cmd)
	return -1
	     
    return((int)(row[0]))

def updateWordArchive(name, id, relevance):
    global DB

    if DB == None:
        openMySQL()
    if DB == None:
        return -1
    if name == None:
        return -1
    if id == None:
        return -1

    c = DB.cursor()
    try:
	ret = c.execute(
"""INSERT INTO wordsArchive (name, id, relevance) VALUES ('%s', '%d', '%d')""" %
                    (name, id, relevance))
    except:
        try:
	    ret = c.execute(
"""UPDATE wordsArchive SET relevance='%d' where name='%s' and ID='%d'""" %
                    (relevance, name, id))
        except:
	    print "Update word archive (%s, %d, %d) failed command" % (name, id, relevance)
	    print """UPDATE wordsArchive SET relevance='%d' where name='%s' and ID='%d'""" % (relevance, name, id)
	    print sys.exc_type, sys.exc_value
	    return -1
441

442 443
    return ret

444 445
#########################################################################
#									#
446
#                  Word dictionary and analysis routines		#
447 448 449
#									#
#########################################################################

450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468
#
# top 100 english word without the one len < 3 + own set
#
dropWords = {
    'the':0, 'this':0, 'can':0, 'man':0, 'had':0, 'him':0, 'only':0,
    'and':0, 'not':0, 'been':0, 'other':0, 'even':0, 'are':0, 'was':0,
    'new':0, 'most':0, 'but':0, 'when':0, 'some':0, 'made':0, 'from':0,
    'who':0, 'could':0, 'after':0, 'that':0, 'will':0, 'time':0, 'also':0,
    'have':0, 'more':0, 'these':0, 'did':0, 'was':0, 'two':0, 'many':0,
    'they':0, 'may':0, 'before':0, 'for':0, 'which':0, 'out':0, 'then':0,
    'must':0, 'one':0, 'through':0, 'with':0, 'you':0, 'said':0,
    'first':0, 'back':0, 'were':0, 'what':0, 'any':0, 'years':0, 'his':0,
    'her':0, 'where':0, 'all':0, 'its':0, 'now':0, 'much':0, 'she':0,
    'about':0, 'such':0, 'your':0, 'there':0, 'into':0, 'like':0, 'may':0,
    'would':0, 'than':0, 'our':0, 'well':0, 'their':0, 'them':0, 'over':0,
    'down':0,
    'net':0, 'www':0, 'bad':0, 'Okay':0, 'bin':0, 'cur':0,
}

469
wordsDict = {}
470
wordsDictHTML = {}
471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499
wordsDictArchive = {}

def cleanupWordsString(str):
    str = string.replace(str, ".", " ")
    str = string.replace(str, "!", " ")
    str = string.replace(str, "?", " ")
    str = string.replace(str, ",", " ")
    str = string.replace(str, "'", " ")
    str = string.replace(str, '"', " ")
    str = string.replace(str, ";", " ")
    str = string.replace(str, "(", " ")
    str = string.replace(str, ")", " ")
    str = string.replace(str, "{", " ")
    str = string.replace(str, "}", " ")
    str = string.replace(str, "<", " ")
    str = string.replace(str, ">", " ")
    str = string.replace(str, "=", " ")
    str = string.replace(str, "/", " ")
    str = string.replace(str, "*", " ")
    str = string.replace(str, ":", " ")
    str = string.replace(str, "#", " ")
    str = string.replace(str, "\\", " ")
    str = string.replace(str, "\n", " ")
    str = string.replace(str, "\r", " ")
    str = string.replace(str, "\xc2", " ")
    str = string.replace(str, "\xa0", " ")
    return str
    
def cleanupDescrString(str):
500
    str = string.replace(str, "'", " ")
501 502 503 504 505 506 507
    str = string.replace(str, "\n", " ")
    str = string.replace(str, "\r", " ")
    str = string.replace(str, "\xc2", " ")
    str = string.replace(str, "\xa0", " ")
    l = string.split(str)
    str = string.join(str)
    return str
508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533

def splitIdentifier(str):
    ret = []
    while str != "":
        cur = string.lower(str[0])
	str = str[1:]
	if ((cur < 'a') or (cur > 'z')):
	    continue
	while (str != "") and (str[0] >= 'A') and (str[0] <= 'Z'):
	    cur = cur + string.lower(str[0])
	    str = str[1:]
	while (str != "") and (str[0] >= 'a') and (str[0] <= 'z'):
	    cur = cur + str[0]
	    str = str[1:]
	while (str != "") and (str[0] >= '0') and (str[0] <= '9'):
	    str = str[1:]
	ret.append(cur)
    return ret

def addWord(word, module, symbol, relevance):
    global wordsDict

    if word == None or len(word) < 3:
        return -1
    if module == None or symbol == None:
        return -1
534 535 536 537 538
    if dropWords.has_key(word):
        return 0
    if ord(word[0]) > 0x80:
        return 0

539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558
    if wordsDict.has_key(word):
        d = wordsDict[word]
	if d == None:
	    return 0
	if len(d) > 500:
	    wordsDict[word] = None
	    return 0
	try:
	    relevance = relevance + d[(module, symbol)]
	except:
	    pass
    else:
        wordsDict[word] = {}
    wordsDict[word][(module, symbol)] = relevance
    return relevance
    
def addString(str, module, symbol, relevance):
    if str == None or len(str) < 3:
        return -1
    ret = 0
559
    str = cleanupWordsString(str)
560 561 562 563 564 565 566
    l = string.split(str)
    for word in l:
	if len(word) > 2:
	    ret = ret + addWord(word, module, symbol, 5)

    return ret

567 568 569 570 571 572 573
def addWordHTML(word, resource, id, section, relevance):
    global wordsDictHTML

    if word == None or len(word) < 3:
        return -1
    if resource == None or section == None:
        return -1
574 575 576 577 578 579
    if dropWords.has_key(word):
        return 0
    if ord(word[0]) > 0x80:
        return 0

    section = cleanupDescrString(section)
580 581 582 583

    if wordsDictHTML.has_key(word):
        d = wordsDictHTML[word]
	if d == None:
584
	    print "skipped %s" % (word)
585 586 587 588 589 590 591 592 593 594 595 596
	    return 0
	try:
	    (r,i,s) = d[resource]
	    if i != None:
	        id = i
	    if s != None:
	        section = s
	    relevance = relevance + r
	except:
	    pass
    else:
        wordsDictHTML[word] = {}
597 598
    d = wordsDictHTML[word];
    d[resource] = (relevance, id, section)
599 600 601 602 603 604
    return relevance
    
def addStringHTML(str, resource, id, section, relevance):
    if str == None or len(str) < 3:
        return -1
    ret = 0
605
    str = cleanupWordsString(str)
606 607 608
    l = string.split(str)
    for word in l:
	if len(word) > 2:
609 610
	    try:
		r = addWordHTML(word, resource, id, section, relevance)
611
		if r < 0:
612 613 614 615 616
		    print "addWordHTML failed: %s %s" % (word, resource)
		ret = ret + r
	    except:
		print "addWordHTML failed: %s %s %d" % (word, resource, relevance)
		print sys.exc_type, sys.exc_value
617 618 619

    return ret

620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666
def addWordArchive(word, id, relevance):
    global wordsDictArchive

    if word == None or len(word) < 3:
        return -1
    if id == None or id == -1:
        return -1
    if dropWords.has_key(word):
        return 0
    if ord(word[0]) > 0x80:
        return 0

    if wordsDictArchive.has_key(word):
        d = wordsDictArchive[word]
	if d == None:
	    print "skipped %s" % (word)
	    return 0
	try:
	    r = d[id]
	    relevance = relevance + r
	except:
	    pass
    else:
        wordsDictArchive[word] = {}
    d = wordsDictArchive[word];
    d[id] = relevance
    return relevance
    
def addStringArchive(str, id, relevance):
    if str == None or len(str) < 3:
        return -1
    ret = 0
    str = cleanupWordsString(str)
    l = string.split(str)
    for word in l:
        i = len(word)
	if i > 2:
	    try:
		r = addWordArchive(word, id, relevance)
		if r < 0:
		    print "addWordArchive failed: %s %s" % (word, id)
		else:
		    ret = ret + r
	    except:
		print "addWordArchive failed: %s %s %d" % (word, id, relevance)
		print sys.exc_type, sys.exc_value
    return ret
667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792

#########################################################################
#									#
#                  XML API description analysis				#
#									#
#########################################################################

def loadAPI(filename):
    doc = libxml2.parseFile(filename)
    print "loaded %s" % (filename)
    return doc

def foundExport(file, symbol):
    if file == None:
        return 0
    if symbol == None:
        return 0
    addFunction(symbol, file)
    l = splitIdentifier(symbol)
    for word in l:
	addWord(word, file, symbol, 10)
    return 1
     
def analyzeAPIFile(top):
    count = 0
    name = top.prop("name")
    cur = top.children
    while cur != None:
        if cur.type == 'text':
	    cur = cur.next
	    continue
	if cur.name == "exports":
	    count = count + foundExport(name, cur.prop("symbol"))
	else:
	    print "unexpected element %s in API doc <file name='%s'>" % (name)
        cur = cur.next
    return count

def analyzeAPIFiles(top):
    count = 0
    cur = top.children
        
    while cur != None:
        if cur.type == 'text':
	    cur = cur.next
	    continue
	if cur.name == "file":
	    count = count + analyzeAPIFile(cur)
	else:
	    print "unexpected element %s in API doc <files>" % (cur.name)
        cur = cur.next
    return count

def analyzeAPIEnum(top):
    file = top.prop("file")
    if file == None:
        return 0
    symbol = top.prop("name")
    if symbol == None:
        return 0

    addEnum(symbol, file)
    l = splitIdentifier(symbol)
    for word in l:
	addWord(word, file, symbol, 10)

    return 1

def analyzeAPIConst(top):
    file = top.prop("file")
    if file == None:
        return 0
    symbol = top.prop("name")
    if symbol == None:
        return 0

    addConst(symbol, file)
    l = splitIdentifier(symbol)
    for word in l:
	addWord(word, file, symbol, 10)

    return 1

def analyzeAPIType(top):
    file = top.prop("file")
    if file == None:
        return 0
    symbol = top.prop("name")
    if symbol == None:
        return 0

    addType(symbol, file)
    l = splitIdentifier(symbol)
    for word in l:
	addWord(word, file, symbol, 10)
    return 1

def analyzeAPIFunctype(top):
    file = top.prop("file")
    if file == None:
        return 0
    symbol = top.prop("name")
    if symbol == None:
        return 0

    addFunctype(symbol, file)
    l = splitIdentifier(symbol)
    for word in l:
	addWord(word, file, symbol, 10)
    return 1

def analyzeAPIStruct(top):
    file = top.prop("file")
    if file == None:
        return 0
    symbol = top.prop("name")
    if symbol == None:
        return 0

    addStruct(symbol, file)
    l = splitIdentifier(symbol)
    for word in l:
	addWord(word, file, symbol, 10)

    info = top.prop("info")
    if info != None:
793 794
	info = string.replace(info, "'", " ")
	info = string.strip(info)
795 796 797 798 799 800 801 802 803 804 805 806 807
	l = string.split(info)
	for word in l:
	    if len(word) > 2:
		addWord(word, file, symbol, 5)
    return 1

def analyzeAPIMacro(top):
    file = top.prop("file")
    if file == None:
        return 0
    symbol = top.prop("name")
    if symbol == None:
        return 0
808 809
    symbol = string.replace(symbol, "'", " ")
    symbol = string.strip(symbol)
810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830

    info = None
    cur = top.children
    while cur != None:
        if cur.type == 'text':
	    cur = cur.next
	    continue
	if cur.name == "info":
	    info = cur.content
	    break
        cur = cur.next

    l = splitIdentifier(symbol)
    for word in l:
	addWord(word, file, symbol, 10)

    if info == None:
	addMacro(symbol, file)
        print "Macro %s description has no <info>" % (symbol)
        return 0

831 832
    info = string.replace(info, "'", " ")
    info = string.strip(info)
833 834 835 836 837 838 839 840 841 842 843 844 845 846 847
    addMacro(symbol, file, info)
    l = string.split(info)
    for word in l:
	if len(word) > 2:
	    addWord(word, file, symbol, 5)
    return 1

def analyzeAPIFunction(top):
    file = top.prop("file")
    if file == None:
        return 0
    symbol = top.prop("name")
    if symbol == None:
        return 0

848 849
    symbol = string.replace(symbol, "'", " ")
    symbol = string.strip(symbol)
850 851 852 853 854 855 856 857 858 859 860
    info = None
    cur = top.children
    while cur != None:
        if cur.type == 'text':
	    cur = cur.next
	    continue
	if cur.name == "info":
	    info = cur.content
	elif cur.name == "return":
	    rinfo = cur.prop("info")
	    if rinfo != None:
861 862
		rinfo = string.replace(rinfo, "'", " ")
		rinfo = string.strip(rinfo)
863 864 865
	        addString(rinfo, file, symbol, 7)
	elif cur.name == "arg":
	    ainfo = cur.prop("info")
866 867 868
	    if ainfo != None:
		ainfo = string.replace(ainfo, "'", " ")
		ainfo = string.strip(ainfo)
869 870 871
	        addString(ainfo, file, symbol, 5)
	    name = cur.prop("name")
	    if name != None:
872 873
		name = string.replace(name, "'", " ")
		name = string.strip(name)
874 875 876 877 878 879
	        addWord(name, file, symbol, 7)
        cur = cur.next
    if info == None:
        print "Function %s description has no <info>" % (symbol)
	addFunction(symbol, file, "")
    else:
880 881
        info = string.replace(info, "'", " ")
	info = string.strip(info)
882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940
	addFunction(symbol, file, info)
        addString(info, file, symbol, 5)

    l = splitIdentifier(symbol)
    for word in l:
	addWord(word, file, symbol, 10)

    return 1

def analyzeAPISymbols(top):
    count = 0
    cur = top.children
        
    while cur != None:
        if cur.type == 'text':
	    cur = cur.next
	    continue
	if cur.name == "macro":
	    count = count + analyzeAPIMacro(cur)
	elif cur.name == "function":
	    count = count + analyzeAPIFunction(cur)
	elif cur.name == "const":
	    count = count + analyzeAPIConst(cur)
	elif cur.name == "typedef":
	    count = count + analyzeAPIType(cur)
	elif cur.name == "struct":
	    count = count + analyzeAPIStruct(cur)
	elif cur.name == "enum":
	    count = count + analyzeAPIEnum(cur)
	elif cur.name == "functype":
	    count = count + analyzeAPIFunctype(cur)
	else:
	    print "unexpected element %s in API doc <files>" % (cur.name)
        cur = cur.next
    return count

def analyzeAPI(doc):
    count = 0
    if doc == None:
        return -1
    root = doc.getRootElement()
    if root.name != "api":
        print "Unexpected root name"
        return -1
    cur = root.children
    while cur != None:
        if cur.type == 'text':
	    cur = cur.next
	    continue
	if cur.name == "files":
	    pass
#	    count = count + analyzeAPIFiles(cur)
	elif cur.name == "symbols":
	    count = count + analyzeAPISymbols(cur)
	else:
	    print "unexpected element %s in API doc" % (cur.name)
        cur = cur.next
    return count

941 942 943 944 945 946 947 948
#########################################################################
#									#
#                  Web pages parsing and analysis			#
#									#
#########################################################################

import glob

949 950 951 952 953 954 955 956 957
def analyzeHTMLText(doc, resource, p, section, id):
    words = 0
    try:
	content = p.content
	words = words + addStringHTML(content, resource, id, section, 5)
    except:
        return -1
    return words

958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975
def analyzeHTMLPara(doc, resource, p, section, id):
    words = 0
    try:
	content = p.content
	words = words + addStringHTML(content, resource, id, section, 5)
    except:
        return -1
    return words

def analyzeHTMLPre(doc, resource, p, section, id):
    words = 0
    try:
	content = p.content
	words = words + addStringHTML(content, resource, id, section, 5)
    except:
        return -1
    return words

976 977 978 979 980 981 982 983 984
def analyzeHTML(doc, resource, p, section, id):
    words = 0
    try:
	content = p.content
	words = words + addStringHTML(content, resource, id, section, 5)
    except:
        return -1
    return words

985 986 987 988 989 990 991 992 993 994
def analyzeHTML(doc, resource):
    para = 0;
    ctxt = doc.xpathNewContext()
    try:
	res = ctxt.xpathEval("//head/title")
	title = res[0].content
    except:
        title = "Page %s" % (resource)
    addPage(resource, title)
    try:
995
	items = ctxt.xpathEval("//h1 | //h2 | //h3 | //text()")
996 997 998 999 1000 1001 1002 1003 1004
	section = title
	id = ""
	for item in items:
	    if item.name == 'h1' or item.name == 'h2' or item.name == 'h3':
	        section = item.content
		if item.prop("id"):
		    id = item.prop("id")
		elif item.prop("name"):
		    id = item.prop("name")
1005 1006 1007
	    elif item.type == 'text':
	        analyzeHTMLText(doc, resource, item, section, id)
		para = para + 1
1008
	    elif item.name == 'p':
1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030
	        analyzeHTMLPara(doc, resource, item, section, id)
		para = para + 1
	    elif item.name == 'pre':
	        analyzeHTMLPre(doc, resource, item, section, id)
		para = para + 1
	    else:
	        print "Page %s, unexpected %s element" % (resource, item.name)
    except:
        print "Page %s: problem analyzing" % (resource)
	print sys.exc_type, sys.exc_value

    return para

def analyzeHTMLPages():
    ret = 0
    HTMLfiles = glob.glob("*.html") + glob.glob("tutorial/*.html")
    for html in HTMLfiles:
	if html[0:3] == "API":
	    continue
	if html == "xml.html":
	    continue
	try:
1031 1032
	    doc = libxml2.parseFile(html)
	except:
1033
	    doc = libxml2.htmlParseFile(html, None)
1034
	try:
1035 1036 1037 1038 1039 1040 1041
	    res = analyzeHTML(doc, html)
	    print "Parsed %s : %d paragraphs" % (html, res)
	    ret = ret + 1
	except:
	    print "could not parse %s" % (html)
    return ret

1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089
#########################################################################
#									#
#                  Mail archives parsing and analysis			#
#									#
#########################################################################

import time

def getXMLDateArchive(t = None):
    if t == None:
	t = time.time()
    T = time.gmtime(t)
    month = time.strftime("%B", T)
    year = T[0]
    url = "http://mail.gnome.org/archives/xml/%d-%s/date.html" % (year, month)
    return url

def scanXMLMsgArchive(url, title, force = 0):
    if url == None or title == None:
        return 0

    ID = checkXMLMsgArchive(url)
    if force == 0 and ID != -1:
        return 0

    if ID == -1:
	ID = addXMLMsgArchive(url, title)
	if ID == -1:
	    return 0

    try:
        print "Loading %s" % (url)
        doc = libxml2.htmlParseFile(url, None);
    except:
        doc = None
    if doc == None:
        print "Failed to parse %s" % (url)
	return 0

    addStringArchive(title, ID, 20)
    ctxt = doc.xpathNewContext()
    texts = ctxt.xpathEval("//pre//text()")
    for text in texts:
        addStringArchive(text.content, ID, 5)

    return 1

def scanXMLDateArchive(t = None, force = 0):
1090 1091 1092 1093
    global wordsDictArchive

    wordsDictArchive = {}

1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127
    url = getXMLDateArchive(t)
    print "loading %s" % (url)
    try:
	doc = libxml2.htmlParseFile(url, None);
    except:
        doc = None
    if doc == None:
        print "Failed to parse %s" % (url)
	return -1
    ctxt = doc.xpathNewContext()
    anchors = ctxt.xpathEval("//a[@href]")
    links = 0
    newmsg = 0
    for anchor in anchors:
	href = anchor.prop("href")
	if href == None or href[0:3] != "msg":
	    continue
        try:
	    links = links + 1

	    msg = libxml2.buildURI(href, url)
	    title = anchor.content
	    if title != None and title[0:4] == 'Re: ':
	        title = title[4:]
	    if title != None and title[0:6] == '[xml] ':
	        title = title[6:]
	    newmsg = newmsg + scanXMLMsgArchive(msg, title, force)

	except:
	    pass

    return newmsg
    

1128 1129 1130 1131 1132
#########################################################################
#									#
#          Main code: open the DB, the API XML and analyze it		#
#									#
#########################################################################
1133 1134
def analyzeArchives(t = None, force = 0):
    global wordsDictArchive
1135

1136 1137
    ret = scanXMLDateArchive(t, force)
    print "Indexed %d words in %d archive pages" % (len(wordsDictArchive), ret)
1138

1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152
    i = 0
    skipped = 0
    for word in wordsDictArchive.keys():
	refs = wordsDictArchive[word]
	if refs  == None:
	    skipped = skipped + 1
	    continue;
	for id in refs.keys():
	    relevance = refs[id]
	    updateWordArchive(word, id, relevance)
	    i = i + 1

    print "Found %d associations in HTML pages" % (i)

1153
def analyzeHTMLTop():
1154
    global wordsDictHTML
1155

1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172
    ret = analyzeHTMLPages()
    print "Indexed %d words in %d HTML pages" % (len(wordsDictHTML), ret)

    i = 0
    skipped = 0
    for word in wordsDictHTML.keys():
	refs = wordsDictHTML[word]
	if refs  == None:
	    skipped = skipped + 1
	    continue;
	for resource in refs.keys():
	    (relevance, id, section) = refs[resource]
	    updateWordHTML(word, resource, section, id, relevance)
	    i = i + 1

    print "Found %d associations in HTML pages" % (i)

1173
def analyzeAPITop():
1174
    global wordsDict
1175
    global API
1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201

    try:
	doc = loadAPI(API)
	ret = analyzeAPI(doc)
	print "Analyzed %d blocs" % (ret)
	doc.freeDoc()
    except:
	print "Failed to parse and analyze %s" % (API)
	print sys.exc_type, sys.exc_value
	sys.exit(1)

    print "Indexed %d words" % (len(wordsDict))
    i = 0
    skipped = 0
    for word in wordsDict.keys():
	refs = wordsDict[word]
	if refs  == None:
	    skipped = skipped + 1
	    continue;
	for (module, symbol) in refs.keys():
	    updateWord(word, symbol, refs[(module, symbol)])
	    i = i + 1

    print "Found %d associations, skipped %d words" % (i, skipped)

def usage():
1202
    print "Usage index.py [--force] [--archive]  [--archive-year year] [--archive-month month] [--API] [--docs]"
1203 1204
    sys.exit(1)

1205
def main():
1206 1207 1208 1209 1210 1211 1212
    try:
	openMySQL()
    except:
	print "Failed to open the database"
	print sys.exc_type, sys.exc_value
	sys.exit(1)

1213 1214 1215 1216 1217 1218 1219 1220
    args = sys.argv[1:]
    force = 0
    if args:
        i = 0
	while i < len(args):
	    if args[i] == '--force':
	        force = 1
	    elif args[i] == '--archive':
1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236
	        analyzeArchives(None, force)
	    elif args[i] == '--archive-year':
	        i = i + 1;
		year = args[i]
		months = ["January" , "February", "March", "April", "May",
			  "June", "July", "August", "September", "October",
			  "November", "December"];
	        for month in months:
		    try:
		        str = "%s-%s" % (year, month)
			T = time.strptime(str, "%Y-%B")
			t = time.mktime(T) + 3600 * 24 * 10;
			analyzeArchives(t, force)
		    except:
			print "Failed to index month archive:"
			print sys.exc_type, sys.exc_value
1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247
	    elif args[i] == '--archive-month':
	        i = i + 1;
		month = args[i]
		try:
		    T = time.strptime(month, "%Y-%B")
		    t = time.mktime(T) + 3600 * 24 * 10;
		    analyzeArchives(t, force)
		except:
		    print "Failed to index month archive:"
		    print sys.exc_type, sys.exc_value
	    elif args[i] == '--API':
1248
	        analyzeAPITop()
1249
	    elif args[i] == '--docs':
1250
	        analyzeHTMLTop()
1251 1252 1253 1254 1255 1256 1257 1258
	    else:
	        usage()
	    i = i + 1
    else:
        usage()

if __name__ == "__main__":
    main()