/* Copyright 2012,2013 Jun Wako This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 2 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program. If not, see . */ #ifndef KEYMAP_H #define KEYMAP_H #include #include #include "action.h" #if defined(__AVR__) #include #endif #include "keycode.h" #include "action_macro.h" #include "report.h" #include "host.h" // #include "print.h" #include "debug.h" #include "keycode_config.h" // ChibiOS uses RESET in its FlagStatus enumeration // Therefore define it as QK_RESET here, to avoid name collision #if defined(PROTOCOL_CHIBIOS) #define RESET QK_RESET #endif /* translates key to keycode */ uint16_t keymap_key_to_keycode(uint8_t layer, keypos_t key); extern const uint16_t keymaps[][MATRIX_ROWS][MATRIX_COLS]; extern const uint16_t fn_actions[]; enum quantum_keycodes { // Ranges used in shortucuts - not to be used directly QK_TMK = 0x0000, QK_TMK_MAX = 0x00FF, QK_MODS = 0x0100, QK_LCTL = 0x0100, QK_LSFT = 0x0200, QK_LALT = 0x0400, QK_LGUI = 0x0800, QK_RCTL = 0x1100, QK_RSFT = 0x1200, QK_RALT = 0x1400, QK_RGUI = 0x1800, QK_MODS_MAX = 0x1FFF, QK_FUNCTION = 0x2000, QK_FUNCTION_MAX = 0x2FFF, QK_MACRO = 0x3000, QK_MACRO_MAX = 0x3FFF, QK_LAYER_TAP = 0x4000, QK_LAYER_TAP_MAX = 0x4FFF, QK_TO = 0x5000, QK_TO_MAX = 0x50FF, QK_MOMENTARY = 0x5100, QK_MOMENTARY_MAX = 0x51FF, QK_DEF_LAYER = 0x5200, QK_DEF_LAYER_MAX = 0x52FF, QK_TOGGLE_LAYER = 0x5300, QK_TOGGLE_LAYER_MAX = 0x53FF, QK_ONE_SHOT_LAYER = 0x5400, QK_ONE_SHOT_LAYER_MAX = 0x54FF, QK_ONE_SHOT_MOD = 0x5500, QK_ONE_SHOT_MOD_MAX = 0x55FF, #ifndef DISABLE_CHORDING QK_CHORDING = 0x5600, QK_CHORDING_MAX = 0x56FF, #endif QK_MOD_TAP = 0x6000, QK_MOD_TAP_MAX = 0x6FFF, QK_TAP_DANCE = 0x7100, QK_TAP_DANCE_MAX = 0x71FF, #ifdef UNICODE_ENABLE QK_UNICODE = 0x8000, QK_UNICODE_MAX = 0xFFFF, #endif // Loose keycodes - to be used directly RESET = 0x7000, DEBUG, MAGIC_SWAP_CONTROL_CAPSLOCK, MAGIC_CAPSLOCK_TO_CONTROL, MAGIC_SWAP_LALT_LGUI, MAGIC_SWAP_RALT_RGUI, MAGIC_NO_GUI, MAGIC_SWAP_GRAVE_ESC, MAGIC_SWAP_BACKSLASH_BACKSPACE, MAGIC_HOST_NKRO, MAGIC_SWAP_ALT_GUI, MAGIC_UNSWAP_CONTROL_CAPSLOCK, MAGIC_UNCAPSLOCK_TO_CONTROL, MAGIC_UNSWAP_LALT_LGUI, MAGIC_UNSWAP_RALT_RGUI, MAGIC_UNNO_GUI, MAGIC_UNSWAP_GRAVE_ESC, MAGIC_UNSWAP_BACKSLASH_BACKSPACE, MAGIC_UNHOST_NKRO, MAGIC_UNSWAP_ALT_GUI, MAGIC_TOGGLE_NKRO, // Leader key #ifndef DISABLE_LEADER KC_LEAD, #endif // Audio on/off/toggle AU_ON, AU_OFF, AU_TOG, // Music mode on/off/toggle MU_ON, MU_OFF, MU_TOG, // Music voice iterate MUV_IN, MUV_DE, // Midi mode on/off MIDI_ON, MIDI_OFF, // Backlight functionality BL_0, BL_1, BL_2, BL_3, BL_4, BL_5, BL_6, BL_7, BL_8, BL_9, BL_10, BL_11, BL_12, BL_13, BL_14, BL_15, BL_DEC, BL_INC, BL_TOGG, BL_STEP, // RGB functionality RGB_TOG, RGB_MOD, RGB_HUI, RGB_HUD, RGB_SAI, RGB_SAD, RGB_VAI, RGB_VAD, // Left shift, open paren KC_LSPO, // Right shift, close paren KC_RSPC, // always leave at the end SAFE_RANGE }; // Ability to use mods in layouts #define LCTL(kc) (kc | QK_LCTL) #define LSFT(kc) (kc | QK_LSFT) #define LALT(kc) (kc | QK_LALT) #define LGUI(kc) (kc | QK_LGUI) #define RCTL(kc) (kc | QK_RCTL) #define RSFT(kc) (kc | QK_RSFT) #define RALT(kc) (kc | QK_RALT) #define RGUI(kc) (kc | QK_RGUI) #define HYPR(kc) (kc | QK_LCTL | QK_LSFT | QK_LALT | QK_LGUI) #define MEH(kc) (kc | QK_LCTL | QK_LSFT | QK_LALT) #define LCAG(kc) (kc | QK_LCTL | QK_LALT | QK_LGUI) #define MOD_HYPR 0xf #define MOD_MEH 0x7 // Aliases for shifted symbols // Each key has a 4-letter code, and some have longer aliases too. // While the long aliases are descriptive, the 4-letter codes // make for nicer grid layouts (everything lines up), and are // the preferred style for Quantum. #define KC_TILD LSFT(KC_GRV) // ~ #define KC_TILDE KC_TILD #define KC_EXLM LSFT(KC_1) // ! #define KC_EXCLAIM KC_EXLM #define KC_AT LSFT(KC_2) // @ #define KC_HASH LSFT(KC_3) // # #define KC_DLR LSFT(KC_4) // $ #define KC_DOLLAR KC_DLR #define KC_PERC LSFT(KC_5) // % #define KC_PERCENT KC_PERC #define KC_CIRC LSFT(KC_6) // ^ #define KC_CIRCUMFLEX KC_CIRC #define KC_AMPR LSFT(KC_7) // & #define KC_AMPERSAND KC_AMPR #define KC_ASTR LSFT(KC_8) // * #define KC_ASTERISK KC_ASTR #define KC_LPRN LSFT(KC_9) // ( #define KC_LEFT_PAREN KC_LPRN #define KC_RPRN LSFT(KC_0) // ) #define KC_RIGHT_PAREN KC_RPRN #define KC_UNDS LSFT(KC_MINS) // _ #define KC_UNDERSCORE KC_UNDS #define KC_PLUS LSFT(KC_EQL) // + #define KC_LCBR LSFT(KC_LBRC) // { #define KC_LEFT_CURLY_BRACE KC_LCBR #define KC_RCBR LSFT(KC_RBRC) // } #define KC_RIGHT_CURLY_BRACE KC_RCBR #define KC_LABK LSFT(KC_COMM) // < #define KC_LEFT_ANGLE_BRACKET KC_LABK #define KC_RABK LSFT(KC_DOT) // > #define KC_RIGHT_ANGLE_BRACKET KC_RABK #define KC_COLN LSFT(KC_SCLN) // : #define KC_COLON KC_COLN #define KC_PIPE LSFT(KC_BSLS) // | #define KC_LT LSFT(KC_COMM) // < #define KC_GT LSFT(KC_DOT) // > #define KC_QUES LSFT(KC_SLSH) // ? #define KC_QUESTION KC_QUES #define KC_DQT LSFT(KC_QUOT) // " #define KC_DOUBLE_QUOTE KC_DQT #define KC_DQUO KC_DQT #define KC_DELT KC_DELETE // Del key (four letter code) // Alias for function layers than expand past FN31 #define FUNC(kc) (kc | QK_FUNCTION) // Aliases #define S(kc) LSFT(kc) #define F(kc) FUNC(kc) #define M(kc) (kc | QK_MACRO) #define MACRODOWN(...) (record->event.pressed ? MACRO(__VA_ARGS__) : MACRO_NONE) // L-ayer, T-ap - 256 keycode max, 16 layer max #define LT(layer, kc) (kc | QK_LAYER_TAP | ((layer & 0xF) << 8)) #define AG_SWAP MAGIC_SWAP_ALT_GUI #define AG_NORM MAGIC_UNSWAP_ALT_GUI #define BL_ON BL_9 #define BL_OFF BL_0 #define MI_ON MIDI_ON #define MI_OFF MIDI_OFF // GOTO layer - 16 layers max // when: // ON_PRESS = 1 // ON_RELEASE = 2 // Unless you have a good reason not to do so, prefer ON_PRESS (1) as your default. #define TO(layer, when) (layer | QK_TO | (when << 0x4)) // Momentary switch layer - 256 layer max #define MO(layer) (layer | QK_MOMENTARY) // Set default layer - 256 layer max #define DF(layer) (layer | QK_DEF_LAYER) // Toggle to layer - 256 layer max #define TG(layer) (layer | QK_TOGGLE_LAYER) // One-shot layer - 256 layer max #define OSL(layer) (layer | QK_ONE_SHOT_LAYER) // One-shot mod #define OSM(mod) (mod | QK_ONE_SHOT_MOD) // M-od, T-ap - 256 keycode max #define MT(mod, kc) (kc | QK_MOD_TAP | ((mod & 0xF) << 8)) #define CTL_T(kc) MT(MOD_LCTL, kc) #define SFT_T(kc) MT(MOD_LSFT, kc) #define ALT_T(kc) MT(MOD_LALT, kc) #define GUI_T(kc) MT(MOD_LGUI, kc) #define C_S_T(kc) MT((MOD_LCTL | MOD_LSFT), kc) // Control + Shift e.g. for gnome-terminal #define MEH_T(kc) MT((MOD_LCTL | MOD_LSFT | MOD_LALT), kc) // Meh is a less hyper version of the Hyper key -- doesn't include Win or Cmd, so just alt+shift+ctrl #define LCAG_T(kc) MT((MOD_LCTL | MOD_LALT | MOD_LGUI), kc) // Left control alt and gui #define ALL_T(kc) MT((MOD_LCTL | MOD_LSFT | MOD_LALT | MOD_LGUI), kc) // see http://brettterpstra.com/2012/12/08/a-useful-caps-lock-key/ // Dedicated keycode versions for Hyper and Meh, if you want to use them as standalone keys rather than mod-tap #define KC_HYPR HYPR(KC_NO) #define KC_MEH MEH(KC_NO) #ifdef UNICODE_ENABLE // For sending unicode codes. // You may not send codes over 7FFF -- this supports most of UTF8. // To have a key that sends out Œ, go UC(0x0152) #define UNICODE(n) (n | QK_UNICODE) #define UC(n) UNICODE(n) #endif #endif 169' href='#n169'>169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 
#!/usr/bin/env python
"""html2text: Turn HTML into equivalent Markdown-structured text."""
__version__ = "3.200.3"
__author__ = "Aaron Swartz (me@aaronsw.com)"
__copyright__ = "(C) 2004-2008 Aaron Swartz. GNU GPL 3."
__contributors__ = ["Martin 'Joey' Schulze", "Ricardo Reyes", "Kevin Jay North"]

# TODO:
#   Support decoded entities with unifiable.

try:
    True
except NameError:
    setattr(__builtins__, 'True', 1)
    setattr(__builtins__, 'False', 0)

def has_key(x, y):
    if hasattr(x, 'has_key'): return x.has_key(y)
    else: return y in x

try:
    import htmlentitydefs
    import urlparse
    import HTMLParser
except ImportError: #Python3
    import html.entities as htmlentitydefs
    import urllib.parse as urlparse
    import html.parser as HTMLParser
try: #Python3
    import urllib.request as urllib
except:
    import urllib
import optparse, re, sys, codecs, types

try: from textwrap import wrap
except: pass

# Use Unicode characters instead of their ascii psuedo-replacements
UNICODE_SNOB = 0

# Put the links after each paragraph instead of at the end.
LINKS_EACH_PARAGRAPH = 0

# Wrap long lines at position. 0 for no wrapping. (Requires Python 2.3.)
BODY_WIDTH = 78

# Don't show internal links (href="#local-anchor") -- corresponding link targets
# won't be visible in the plain text file anyway.
SKIP_INTERNAL_LINKS = True

# Use inline, rather than reference, formatting for images and links
INLINE_LINKS = True

# Number of pixels Google indents nested lists
GOOGLE_LIST_INDENT = 36

IGNORE_ANCHORS = False
IGNORE_IMAGES = False
IGNORE_EMPHASIS = False

### Entity Nonsense ###

def name2cp(k):
    if k == 'apos': return ord("'")
    if hasattr(htmlentitydefs, "name2codepoint"): # requires Python 2.3
        return htmlentitydefs.name2codepoint[k]
    else:
        k = htmlentitydefs.entitydefs[k]
        if k.startswith("&#") and k.endswith(";"): return int(k[2:-1]) # not in latin-1
        return ord(codecs.latin_1_decode(k)[0])

unifiable = {'rsquo':"'", 'lsquo':"'", 'rdquo':'"', 'ldquo':'"',
'copy':'(C)', 'mdash':'--', 'nbsp':' ', 'rarr':'->', 'larr':'<-', 'middot':'*',
'ndash':'-', 'oelig':'oe', 'aelig':'ae',
'agrave':'a', 'aacute':'a', 'acirc':'a', 'atilde':'a', 'auml':'a', 'aring':'a',
'egrave':'e', 'eacute':'e', 'ecirc':'e', 'euml':'e',
'igrave':'i', 'iacute':'i', 'icirc':'i', 'iuml':'i',
'ograve':'o', 'oacute':'o', 'ocirc':'o', 'otilde':'o', 'ouml':'o',
'ugrave':'u', 'uacute':'u', 'ucirc':'u', 'uuml':'u',
'lrm':'', 'rlm':''}

unifiable_n = {}

for k in unifiable.keys():
    unifiable_n[name2cp(k)] = unifiable[k]

### End Entity Nonsense ###

def onlywhite(line):
    """Return true if the line does only consist of whitespace characters."""
    for c in line:
        if c is not ' ' and c is not '  ':
            return c is ' '
    return line

def hn(tag):
    if tag[0] == 'h' and len(tag) == 2:
        try:
            n = int(tag[1])
            if n in range(1, 10): return n
        except ValueError: return 0

def dumb_property_dict(style):
    """returns a hash of css attributes"""
    return dict([(x.strip(), y.strip()) for x, y in [z.split(':', 1) for z in style.split(';') if ':' in z]]);

def dumb_css_parser(data):
    """returns a hash of css selectors, each of which contains a hash of css attributes"""
    # remove @import sentences
    importIndex = data.find('@import')
    while importIndex != -1:
        data = data[0:importIndex] + data[data.find(';', importIndex) + 1:]
        importIndex = data.find('@import')

    # parse the css. reverted from dictionary compehension in order to support older pythons
    elements =  [x.split('{') for x in data.split('}') if '{' in x.strip()]
    try:
        elements = dict([(a.strip(), dumb_property_dict(b)) for a, b in elements])
    except ValueError:
        elements = {} # not that important

    return elements

def element_style(attrs, style_def, parent_style):
    """returns a hash of the 'final' style attributes of the element"""
    style = parent_style.copy()
    if 'class' in attrs:
        for css_class in attrs['class'].split():
            css_style = style_def['.' + css_class]
            style.update(css_style)
    if 'style' in attrs:
        immediate_style = dumb_property_dict(attrs['style'])
        style.update(immediate_style)
    return style

def google_list_style(style):
    """finds out whether this is an ordered or unordered list"""
    if 'list-style-type' in style:
        list_style = style['list-style-type']
        if list_style in ['disc', 'circle', 'square', 'none']:
            return 'ul'
    return 'ol'

def google_has_height(style):
    """check if the style of the element has the 'height' attribute explicitly defined"""
    if 'height' in style:
        return True
    return False

def google_text_emphasis(style):
    """return a list of all emphasis modifiers of the element"""
    emphasis = []
    if 'text-decoration' in style:
        emphasis.append(style['text-decoration'])
    if 'font-style' in style:
        emphasis.append(style['font-style'])
    if 'font-weight' in style:
        emphasis.append(style['font-weight'])
    return emphasis

def google_fixed_width_font(style):
    """check if the css of the current element defines a fixed width font"""
    font_family = ''
    if 'font-family' in style:
        font_family = style['font-family']
    if 'Courier New' == font_family or 'Consolas' == font_family:
        return True
    return False

def list_numbering_start(attrs):
    """extract numbering from list element attributes"""
    if 'start' in attrs:
        return int(attrs['start']) - 1
    else:
        return 0

class HTML2Text(HTMLParser.HTMLParser):
    def __init__(self, out=None, baseurl=''):
        HTMLParser.HTMLParser.__init__(self)

        # Config options
        self.unicode_snob = UNICODE_SNOB
        self.links_each_paragraph = LINKS_EACH_PARAGRAPH
        self.body_width = BODY_WIDTH
        self.skip_internal_links = SKIP_INTERNAL_LINKS
        self.inline_links = INLINE_LINKS
        self.google_list_indent = GOOGLE_LIST_INDENT
        self.ignore_links = IGNORE_ANCHORS
        self.ignore_images = IGNORE_IMAGES
        self.ignore_emphasis = IGNORE_EMPHASIS
        self.google_doc = False
        self.ul_item_mark = '*'

        if out is None:
            self.out = self.outtextf
        else:
            self.out = out

        self.outtextlist = []  # empty list to store output characters before they are "joined"

        try:
            self.outtext = unicode()
        except NameError:  # Python3
            self.outtext = str()

        self.quiet = 0
        self.p_p = 0  # number of newline character to print before next output
        self.outcount = 0
        self.start = 1
        self.space = 0
        self.a = []
        self.astack = []
        self.acount = 0
        self.list = []
        self.blockquote = 0
        self.pre = 0
        self.startpre = 0
        self.code = False
        self.br_toggle = ''
        self.lastWasNL = 0
        self.lastWasList = False
        self.style = 0
        self.style_def = {}
        self.tag_stack = []
        self.emphasis = 0
        self.drop_white_space = 0
        self.inheader = False
        self.abbr_title = None  # current abbreviation definition
        self.abbr_data = None  # last inner HTML (for abbr being defined)
        self.abbr_list = {}  # stack of abbreviations to write later
        self.baseurl = baseurl

        try: del unifiable_n[name2cp('nbsp')]
        except KeyError: pass
        unifiable['nbsp'] = '&nbsp_place_holder;'


    def feed(self, data):
        data = data.replace("</' + 'script>", "</ignore>")
        HTMLParser.HTMLParser.feed(self, data)

    def handle(self, data):
        self.feed(data)
        self.feed("")
        return self.optwrap(self.close())

    def outtextf(self, s):
        self.outtextlist.append(s)
        if s: self.lastWasNL = s[-1] == '\n'

    def close(self):
        HTMLParser.HTMLParser.close(self)

        self.pbr()
        self.o('', 0, 'end')

        self.outtext = self.outtext.join(self.outtextlist)
        if self.unicode_snob:
            nbsp = unichr(name2cp('nbsp'))
        else:
            nbsp = u' '
        self.outtext = self.outtext.replace(u'&nbsp_place_holder;', nbsp)

        return self.outtext

    def handle_charref(self, c):
        self.o(self.charref(c), 1)

    def handle_entityref(self, c):
        self.o(self.entityref(c), 1)

    def handle_starttag(self, tag, attrs):
        self.handle_tag(tag, attrs, 1)

    def handle_endtag(self, tag):
        self.handle_tag(tag, None, 0)

    def previousIndex(self, attrs):
        """ returns the index of certain set of attributes (of a link) in the
            self.a list

            If the set of attributes is not found, returns None
        """
        if not has_key(attrs, 'href'): return None

        i = -1
        for a in self.a:
            i += 1
            match = 0

            if has_key(a, 'href') and a['href'] == attrs['href']:
                if has_key(a, 'title') or has_key(attrs, 'title'):
                        if (has_key(a, 'title') and has_key(attrs, 'title') and
                            a['title'] == attrs['title']):
                            match = True
                else:
                    match = True

            if match: return i

    def drop_last(self, nLetters):
        if not self.quiet:
            self.outtext = self.outtext[:-nLetters]

    def handle_emphasis(self, start, tag_style, parent_style):
        """handles various text emphases"""
        tag_emphasis = google_text_emphasis(tag_style)
        parent_emphasis = google_text_emphasis(parent_style)

        # handle Google's text emphasis
        strikethrough =  'line-through' in tag_emphasis and self.hide_strikethrough
        bold = 'bold' in tag_emphasis and not 'bold' in parent_emphasis
        italic = 'italic' in tag_emphasis and not 'italic' in parent_emphasis
        fixed = google_fixed_width_font(tag_style) and not \
                google_fixed_width_font(parent_style) and not self.pre

        if start:
            # crossed-out text must be handled before other attributes
            # in order not to output qualifiers unnecessarily
            if bold or italic or fixed:
                self.emphasis += 1
            if strikethrough:
                self.quiet += 1
            if italic:
                self.o("_")
                self.drop_white_space += 1
            if bold:
                self.o("**")
                self.drop_white_space += 1
            if fixed:
                self.o('`')
                self.drop_white_space += 1
                self.code = True
        else:
            if bold or italic or fixed:
                # there must not be whitespace before closing emphasis mark
                self.emphasis -= 1
                self.space = 0
                self.outtext = self.outtext.rstrip()
            if fixed:
                if self.drop_white_space:
                    # empty emphasis, drop it
                    self.drop_last(1)
                    self.drop_white_space -= 1
                else:
                    self.o('`')
                self.code = False
            if bold:
                if self.drop_white_space:
                    # empty emphasis, drop it
                    self.drop_last(2)
                    self.drop_white_space -= 1
                else:
                    self.o("**")
            if italic:
                if self.drop_white_space:
                    # empty emphasis, drop it
                    self.drop_last(1)
                    self.drop_white_space -= 1
                else:
                    self.o("_")
            # space is only allowed after *all* emphasis marks
            if (bold or italic) and not self.emphasis:
                    self.o(" ")
            if strikethrough:
                self.quiet -= 1

    def handle_tag(self, tag, attrs, start):
        #attrs = fixattrs(attrs)
        if attrs is None:
            attrs = {}
        else:
            attrs = dict(attrs)

        if self.google_doc:
            # the attrs parameter is empty for a closing tag. in addition, we
            # need the attributes of the parent nodes in order to get a
            # complete style description for the current element. we assume
            # that google docs export well formed html.
            parent_style = {}
            if start:
                if self.tag_stack:
                  parent_style = self.tag_stack[-1][2]
                tag_style = element_style(attrs, self.style_def, parent_style)
                self.tag_stack.append((tag, attrs, tag_style))
            else:
                dummy, attrs, tag_style = self.tag_stack.pop()
                if self.tag_stack:
                    parent_style = self.tag_stack[-1][2]

        if hn(tag):
            self.p()
            if start:
                self.inheader = True
                self.o(hn(tag)*"#" + ' ')
            else:
                self.inheader = False
                return # prevent redundant emphasis marks on headers

        if tag in ['p', 'div']:
            if self.google_doc:
                if start and google_has_height(tag_style):
                    self.p()
                else:
                    self.soft_br()
            else:
                self.p()

        if tag == "br" and start: self.o("  \n")

        if tag == "hr" and start:
            self.p()
            self.o("* * *")
            self.p()

        if tag in ["head", "style", 'script']:
            if start: self.quiet += 1
            else: self.quiet -= 1

        if tag == "style":
            if start: self.style += 1
            else: self.style -= 1

        if tag in ["body"]:
            self.quiet = 0 # sites like 9rules.com never close <head>

        if tag == "blockquote":
            if start:
                self.p(); self.o('> ', 0, 1); self.start = 1
                self.blockquote += 1
            else:
                self.blockquote -= 1
                self.p()

        if tag in ['em', 'i', 'u'] and not self.ignore_emphasis: self.o("_")
        if tag in ['strong', 'b'] and not self.ignore_emphasis: self.o("**")
        if tag in ['del', 'strike', 's']:
            if start:
                self.o("<"+tag+">")
            else:
                self.o("</"+tag+">")

        if self.google_doc:
            if not self.inheader:
                # handle some font attributes, but leave headers clean
                self.handle_emphasis(start, tag_style, parent_style)

        if tag in ["code", "tt"] and not self.pre: self.o('`') #TODO: `` `this` ``
        if tag == "abbr":
            if start:
                self.abbr_title = None
                self.abbr_data = ''
                if has_key(attrs, 'title'):
                    self.abbr_title = attrs['title']
            else:
                if self.abbr_title != None:
                    self.abbr_list[self.abbr_data] = self.abbr_title
                    self.abbr_title = None
                self.abbr_data = ''

        if tag == "a" and not self.ignore_links:
            if start:
                if has_key(attrs, 'href') and not (self.skip_internal_links and attrs['href'].startswith('#')):
                    self.astack.append(attrs)
                    self.o("[")
                else:
                    self.astack.append(None)
            else:
                if self.astack:
                    a = self.astack.pop()
                    if a:
                        if self.inline_links:
                            self.o("](" + escape_md(a['href']) + ")")
                        else:
                            i = self.previousIndex(a)
                            if i is not None:
                                a = self.a[i]
                            else:
                                self.acount += 1
                                a['count'] = self.acount
                                a['outcount'] = self.outcount
                                self.a.append(a)
                            self.o("][" + str(a['count']) + "]")

        if tag == "img" and start and not self.ignore_images:
            if has_key(attrs, 'src'):
                attrs['href'] = attrs['src']
                alt = attrs.get('alt', '')
                self.o("![" + escape_md(alt) + "]")

                if self.inline_links:
                    self.o("(" + escape_md(attrs['href']) + ")")
                else:
                    i = self.previousIndex(attrs)
                    if i is not None:
                        attrs = self.a[i]
                    else:
                        self.acount += 1
                        attrs['count'] = self.acount
                        attrs['outcount'] = self.outcount
                        self.a.append(attrs)
                    self.o("[" + str(attrs['count']) + "]")

        if tag == 'dl' and start: self.p()
        if tag == 'dt' and not start: self.pbr()
        if tag == 'dd' and start: self.o('    ')
        if tag == 'dd' and not start: self.pbr()

        if tag in ["ol", "ul"]:
            # Google Docs create sub lists as top level lists
            if (not self.list) and (not self.lastWasList):
                self.p()
            if start:
                if self.google_doc:
                    list_style = google_list_style(tag_style)
                else:
                    list_style = tag
                numbering_start = list_numbering_start(attrs)
                self.list.append({'name':list_style, 'num':numbering_start})
            else:
                if self.list: self.list.pop()
            self.lastWasList = True
        else:
            self.lastWasList = False

        if tag == 'li':
            self.pbr()
            if start:
                if self.list: li = self.list[-1]
                else: li = {'name':'ul', 'num':0}
                if self.google_doc:
                    nest_count = self.google_nest_count(tag_style)
                else:
                    nest_count = len(self.list)
                self.o("  " * nest_count) #TODO: line up <ol><li>s > 9 correctly.
                if li['name'] == "ul": self.o(self.ul_item_mark + " ")
                elif li['name'] == "ol":
                    li['num'] += 1
                    self.o(str(li['num'])+". ")
                self.start = 1

        if tag in ["table", "tr"] and start: self.p()
        if tag == 'td': self.pbr()

        if tag == "pre":
            if start:
                self.startpre = 1
                self.pre = 1
            else:
                self.pre = 0
            self.p()

    def pbr(self):
        if self.p_p == 0:
            self.p_p = 1

    def p(self):
        self.p_p = 2

    def soft_br(self):
        self.pbr()
        self.br_toggle = '  '

    def o(self, data, puredata=0, force=0):
        if self.abbr_data is not None:
            self.abbr_data += data

        if not self.quiet:
            if self.google_doc:
                # prevent white space immediately after 'begin emphasis' marks ('**' and '_')
                lstripped_data = data.lstrip()
                if self.drop_white_space and not (self.pre or self.code):
                    data = lstripped_data
                if lstripped_data != '':
                    self.drop_white_space = 0

            if puredata and not self.pre:
                data = re.sub('\s+', ' ', data)
                if data and data[0] == ' ':
                    self.space = 1
                    data = data[1:]
            if not data and not force: return

            if self.startpre:
                #self.out(" :") #TODO: not output when already one there
                self.startpre = 0

            bq = (">" * self.blockquote)
            if not (force and data and data[0] == ">") and self.blockquote: bq += " "

            if self.pre:
                bq += "    "
                data = data.replace("\n", "\n"+bq)

            if self.start:
                self.space = 0
                self.p_p = 0
                self.start = 0

            if force == 'end':
                # It's the end.
                self.p_p = 0
                self.out("\n")
                self.space = 0

            if self.p_p:
                self.out((self.br_toggle+'\n'+bq)*self.p_p)
                self.space = 0
                self.br_toggle = ''

            if self.space:
                if not self.lastWasNL: self.out(' ')
                self.space = 0

            if self.a and ((self.p_p == 2 and self.links_each_paragraph) or force == "end"):
                if force == "end": self.out("\n")

                newa = []
                for link in self.a:
                    if self.outcount > link['outcount']:
                        self.out("   ["+ str(link['count']) +"]: " + urlparse.urljoin(self.baseurl, link['href']))
                        if has_key(link, 'title'): self.out(" ("+link['title']+")")
                        self.out("\n")
                    else:
                        newa.append(link)

                if self.a != newa: self.out("\n") # Don't need an extra line when nothing was done.

                self.a = newa

            if self.abbr_list and force == "end":
                for abbr, definition in self.abbr_list.items():
                    self.out("  *[" + abbr + "]: " + definition + "\n")

            self.p_p = 0
            self.out(data)
            self.outcount += 1

    def handle_data(self, data):
        if r'\/script>' in data: self.quiet -= 1

        if self.style:
            self.style_def.update(dumb_css_parser(data))

        self.o(data, 1)

    def unknown_decl(self, data): pass

    def charref(self, name):
        if name[0] in ['x','X']:
            c = int(name[1:], 16)
        else:
            c = int(name)

        if not self.unicode_snob and c in unifiable_n.keys():
            return unifiable_n[c]
        else:
            try:
                return unichr(c)
            except NameError: #Python3
                return chr(c)

    def entityref(self, c):
        if not self.unicode_snob and c in unifiable.keys():
            return unifiable[c]
        else:
            try: name2cp(c)
            except KeyError: return "&" + c + ';'
            else:
                try:
                    return unichr(name2cp(c))
                except NameError: #Python3
                    return chr(name2cp(c))

    def replaceEntities(self, s):
        s = s.group(1)
        if s[0] == "#":
            return self.charref(s[1:])
        else: return self.entityref(s)

    r_unescape = re.compile(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));")
    def unescape(self, s):
        return self.r_unescape.sub(self.replaceEntities, s)

    def google_nest_count(self, style):
        """calculate the nesting count of google doc lists"""
        nest_count = 0
        if 'margin-left' in style:
            nest_count = int(style['margin-left'][:-2]) / self.google_list_indent
        return nest_count


    def optwrap(self, text):
        """Wrap all paragraphs in the provided text."""
        if not self.body_width:
            return text

        assert wrap, "Requires Python 2.3."
        result = ''
        newlines = 0
        for para in text.split("\n"):
            if len(para) > 0:
                if not skipwrap(para):
                    for line in wrap(para, self.body_width):
                        result += line + "\n"
                    result += "\n"
                    newlines = 2
                else:
                    if not onlywhite(para):
                        result += para + "\n"
                        newlines = 1
            else:
                if newlines < 2:
                    result += "\n"
                    newlines += 1
        return result

ordered_list_matcher = re.compile(r'\d+\.\s')
unordered_list_matcher = re.compile(r'[-\*\+]\s')
md_chars_matcher = re.compile(r"([\\\[\]\(\)])")

def skipwrap(para):
    # If the text begins with four spaces or one tab, it's a code block; don't wrap
    if para[0:4] == '    ' or para[0] == '\t':
        return True
    # If the text begins with only two "--", possibly preceded by whitespace, that's
    # an emdash; so wrap.
    stripped = para.lstrip()
    if stripped[0:2] == "--" and stripped[2] != "-":
        return False
    # I'm not sure what this is for; I thought it was to detect lists, but there's
    # a <br>-inside-<span> case in one of the tests that also depends upon it.
    if stripped[0:1] == '-' or stripped[0:1] == '*':
        return True
    # If the text begins with a single -, *, or +, followed by a space, or an integer,
    # followed by a ., followed by a space (in either case optionally preceeded by
    # whitespace), it's a list; don't wrap.
    if ordered_list_matcher.match(stripped) or unordered_list_matcher.match(stripped):
        return True
    return False

def wrapwrite(text):
    text = text.encode('utf-8')
    try: #Python3
        sys.stdout.buffer.write(text)
    except AttributeError:
        sys.stdout.write(text)

def html2text(html, baseurl=''):
    h = HTML2Text(baseurl=baseurl)
    return h.handle(html)

def unescape(s, unicode_snob=False):
    h = HTML2Text()
    h.unicode_snob = unicode_snob
    return h.unescape(s)

def escape_md(text):
    """Escapes markdown-sensitive characters."""
    return md_chars_matcher.sub(r"\\\1", text)

def main():
    baseurl = ''

    p = optparse.OptionParser('%prog [(filename|url) [encoding]]',
                              version='%prog ' + __version__)
    p.add_option("--ignore-emphasis", dest="ignore_emphasis", action="store_true",
        default=IGNORE_EMPHASIS, help="don't include any formatting for emphasis")
    p.add_option("--ignore-links", dest="ignore_links", action="store_true",
        default=IGNORE_ANCHORS, help="don't include any formatting for links")
    p.add_option("--ignore-images", dest="ignore_images", action="store_true",
        default=IGNORE_IMAGES, help="don't include any formatting for images")
    p.add_option("-g", "--google-doc", action="store_true", dest="google_doc",
        default=False, help="convert an html-exported Google Document")
    p.add_option("-d", "--dash-unordered-list", action="store_true", dest="ul_style_dash",
        default=False, help="use a dash rather than a star for unordered list items")
    p.add_option("-b", "--body-width", dest="body_width", action="store", type="int",
        default=BODY_WIDTH, help="number of characters per output line, 0 for no wrap")
    p.add_option("-i", "--google-list-indent", dest="list_indent", action="store", type="int",
        default=GOOGLE_LIST_INDENT, help="number of pixels Google indents nested lists")
    p.add_option("-s", "--hide-strikethrough", action="store_true", dest="hide_strikethrough",
        default=False, help="hide strike-through text. only relevent when -g is specified as well")
    (options, args) = p.parse_args()

    # process input
    encoding = "utf-8"
    if len(args) > 0:
        file_ = args[0]
        if len(args) == 2:
            encoding = args[1]
        if len(args) > 2:
            p.error('Too many arguments')

        if file_.startswith('http://') or file_.startswith('https://'):
            baseurl = file_
            j = urllib.urlopen(baseurl)
            data = j.read()
            if encoding is None:
                try:
                    from feedparser import _getCharacterEncoding as enc
                except ImportError:
                    enc = lambda x, y: ('utf-8', 1)
                encoding = enc(j.headers, data)[0]
                if encoding == 'us-ascii':
                    encoding = 'utf-8'
        else:
            data = open(file_, 'rb').read()
            if encoding is None:
                try:
                    from chardet import detect
                except ImportError:
                    detect = lambda x: {'encoding': 'utf-8'}
                encoding = detect(data)['encoding']
    else:
        data = sys.stdin.read()

    data = data.decode(encoding)
    h = HTML2Text(baseurl=baseurl)
    # handle options
    if options.ul_style_dash: h.ul_item_mark = '-'

    h.body_width = options.body_width
    h.list_indent = options.list_indent
    h.ignore_emphasis = options.ignore_emphasis
    h.ignore_links = options.ignore_links
    h.ignore_images = options.ignore_images
    h.google_doc = options.google_doc
    h.hide_strikethrough = options.hide_strikethrough

    wrapwrite(h.handle(data))


if __name__ == "__main__":
    main()
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-19 04:29:39 +0000