Tryag File Manager
Home
-
Turbo Force
Current Path :
/
usr
/
lib
/
python2.4
/
site-packages
/
lxml
/
html
/
Upload File :
New :
File
Dir
//usr/lib/python2.4/site-packages/lxml/html/diff.pyc
m "Gc @ s d k Z d k l Z d k l Z d k Z d k Z d d g Z d Z e d Z d Z d Z d Z d Z d Z d Z d Z d Z e d Z d Z d f d YZ d f d YZ d e f d YZ d Z d Z d Z d Z d Z d Z d e f d YZ d e f d YZ! d! e f d" YZ" e# d# Z$ e# d$ Z% e i& d% e i' e i( B Z) e i& d& e i' e i( B Z* e i& d' e i' e i( B Z+ d( Z, e i& d) Z- d* Z. di Z/ dj Z0 dk Z1 e dW Z2 dX Z3 e i& dY Z4 dZ Z5 d[ Z6 d\ Z7 d] Z8 d^ Z9 d_ Z: e d` Z; da Z< db Z= dc Z> dd Z? de e i@ f df YZA eB dg j o dh k lC ZC eC iD n d S(l N( s etree( s fragment_fromstringt html_annotatet htmldiffc C s d t i t | d | f S( Ns <span title="%s">%s</span>i ( t cgit escapet unicodet versiont text( R R ( ( t2 /usr/lib/python2.4/site-packages/lxml/html/diff.pyt default_markup s c C s g } | D] \ } } | t | | q ~ } | d } x% | d D] } t | | | } qE Wt | } t | | } d i | i S( s doclist should be ordered from oldest to newest, like:: >>> version1 = 'Hello World' >>> version2 = 'Goodbye World' >>> html_annotate([(version1, 'version 1'), ... (version2, 'version 2')]) u'<span title="version 2">Goodbye</span> <span title="version 1">World</span>' The documents must be *fragments* (str/UTF8 or unicode), not complete documents The markup argument is a function to markup the spans of words. This function is called like markup('Hello', 'version 2'), and returns HTML. The first argument is text and never includes any markup. The default uses a span with a title: >>> default_markup('Some Text', 'by Joe') u'<span title="by Joe">Some Text</span>' i i t N( t _[1]t doclistt docR t tokenize_annotatedt tokenlistt cur_tokenst tokenst html_annotate_merge_annotationst compress_tokenst markup_serialize_tokenst markupt resultt joint strip( R R R R R R R R R ( ( R R s 0 c C s0 t | d t } x | D] } | | _ q W| S( sF Tokenize a document and add an annotation attribute to each token t include_hrefsN( t tokenizeR t FalseR t tokt annotation( R R R R ( ( R R : s c C s} t d | d | } | i } xU | D]M \ } } } } } | d j o+ | | | !} | | | !} t | | q( q( Wd S( s Merge the annotations from tokens_old into tokens_new, when the tokens in the new document already existed in the old document. t at bt equalN( t InsensitiveSequenceMatchert tokens_oldt tokens_newt st get_opcodest commandst commandt i1t i2t j1t j2t eq_oldt eq_newt copy_annotations( R! R" R% R, R+ R' R( R* R) R# R& ( ( R R B s c C sP t | t | j p t x) t | | D] \ } } | i | _ q0 Wd S( sN Copy annotations from the tokens listed in src to the tokens in dest N( t lent srct destt AssertionErrort zipt src_tokt dest_tokR ( R/ R0 R4 R3 ( ( R R- O s c C su | d g } xa | d D]U } | d i o3 | i o( | d i | i j o t | | q | i | q W| S( sm Combine adjacent tokens when there is no HTML between the tokens, and they share an annotation i i iN( R R R t post_tagst pre_tagsR t compress_merge_backt append( R R R ( ( R R W s 1c C s | d } t | t j p t | t j o | i | nl t | } | i o | d 7} n | | 7} t | d | i d | i d | i } | i | _ | | d <d S( sY Merge tok into the last element of tokens (modifying the list of tokens in-place). it R6 R5 t trailing_whitespaceN( R t lastt typet tokenR R8 R R R: R6 R5 t mergedR ( R R R; R R> ( ( R R7 f s & c c s xx | D]p } x | i D] } | Vq W| i } | | | i } | i o | d 7} n | Vx | i D] } | Vqi Wq Wd S( sz Serialize the list of tokens into a list of text chunks, calling markup_func around text to add annotations. R9 N( R R= R6 t pret htmlt markup_funcR R: R5 t post( R RA R? R= R@ RB ( ( R R x s c C sF t | } t | } t | | } d i | i } t | S( s Do a diff of the old and new document. The documents are HTML *fragments* (str/UTF8 or unicode), they are not complete documents (i.e., no <html> tag). Returns HTML with <ins> and <del> tags added around the appropriate text. Markup is generally ignored, with the markup from new_html preserved, and possibly some markup from old_html (though it is considered acceptable to lose some of the old markup). Only the words in the HTML are diffed. The exception is <img> tags, which are treated like words, and the href attribute of <a> tags, which are noted inside the tag itself when there are changes. R N( R t old_htmlt old_html_tokenst new_htmlt new_html_tokenst htmldiff_tokensR R R t fixup_ins_del_tags( RC RE R RF RD ( ( R R s c C s t d | d | } | i } g } x | D] \ } } } } } | d j o' | i t | | | !d t q. n | d j p | d j o$ t | | | ! } t | | n | d j p | d j o$ t | | | ! } t | | q. q. Wt | } | S( s] Does a diff on the tokens themselves, returning a list of text chunks (not tokens). R R R t insertt replacet deleteN( R t html1_tokenst html2_tokensR# R$ R% R R& R' R( R) R* t extendt expand_tokenst Truet ins_tokenst merge_insertt del_tokenst merge_deletet cleanup_delete( RL RM R% RS R' R( R) R* R# R R& RQ ( ( R RG s" c c s x{ | D]s } x | i D] } | Vq W| p | i o* | i o | i d Vqb | i Vn x | i D] } | Vql Wq Wd S( se Given a list of tokens, return a generator of the chunks of text for the data in the tokens. R9 N( R R= R6 R? R t hide_when_equalR: R@ R5 RB ( R R R? R= RB ( ( R RO s c C s t | \ } } } | i | | o) | d i d o | d c d 7<n | i d | o* | d i d o | d d | d <n | i | | i d | i | d S( s| doc is the already-handled document (as a list of text chunks); here we add <ins>ins_chunks</ins> to the end of that. iR9 s <ins>s </ins> N( t split_unbalancedt ins_chunkst unbalanced_startt balancedt unbalanced_endR RN t endswithR8 ( RX R RY R[ RZ ( ( R RR s t DEL_STARTc B s t Z RS( N( t __name__t __module__( ( ( R R] s t DEL_ENDc B s t Z RS( N( R^ R_ ( ( ( R R` s t NoDeletesc B s t Z d Z RS( sY Raised when the document no longer contains any pending deletes (DEL_START/DEL_END) ( R^ R_ t __doc__( ( ( R Ra s c C s+ | i t | i | | i t d S( s Adds the text chunks in del_chunks to the document doc (another list of text chunks) with marker to show it is a delete. cleanup_delete later resolves these markers into <del> tags.N( R R8 R] RN t del_chunksR` ( Rc R ( ( R RT s c C s x y t | \ } } } Wn t j o Pn Xt | \ } } } t | | | t | | | | } | o) | d i d o | d c d 7<n | i d | o* | d i d o | d d | d <n | i | | i d | i | | } q W| S( s Cleans up any DEL_START/DEL_END markers in the document, replacing them with <del></del>. To do this while keeping the document valid, it may need to drop some tags (either start or end tags). It may also move the del into adjacent tags to try to move it to a similar location where it was originally located (e.g., moving a delete into preceding <div> tag, if the del looks like (DEL_START, 'Text</div>', DEL_END)i iR9 s <del>s </del> N( t split_deletet chunkst pre_deleteRK t post_deleteRa RW RY RZ R[ t locate_unbalanced_startt locate_unbalanced_endR R\ R8 RN ( Re RY Rf R[ RZ R RK Rg ( ( R RU s* c C s g } g } g } g } xX| D]P} | i d p | i | q n | d d j } | i d i d } | t j o | i | q n | o | oE | d d | j o0 | i | | i \ } } } | | | <qo| oH | i g } | D] \ } } } | | q ~ g } | i | qo| i | q | i | t | | f | i d q W| i g } | D] \ } } } | | q~ g } | D] } | d j o | | qq~ } | | | f S( s] Return (unbalanced_start, balanced, unbalanced_end), where each is a list of text and tag chunks. unbalanced_start is a list of all the tags that are opened, but not closed in this span. Similarly, unbalanced_end is a list of tags that are closed but were not opened. Extracting these might mean some reordering of the chunks.t <i t /i s <>/iN( t startt endt tag_stackRZ Re t chunkt startswithR8 t endtagt splitR t namet empty_tagst popt post tagRN R R. t None( Re Rm Rs Rq Ro Rv RZ R Rl Rw Rn ( ( R RW ( s< 1 12c C sb y | i t } Wn t j o t n X| i t } | | | | d | !| | d f S( s Returns (stuff_before_DEL_START, stuff_inside_DEL_START_END, stuff_after_DEL_END). Returns the first case found (there may be more DEL_STARTs in stuff_after_DEL_END). Raises NoDeletes if there's no DEL_START found. i N( Re t indexR] Rv t ValueErrorRa R` t pos2( Re Rv R{ ( ( R Rd P s c C s x | p Pn | d } | i d i d } | p Pn | d } | t j p | i d o Pn | d d j o Pn | i d i d } | d j o Pn | d j p t d | | | j o' | i d | i | i d q Pq Wd S( s pre_delete and post_delete implicitly point to a place in the document (where the two were split). This moves that point (by popping items from one and pushing them onto the other). It moves the point to try to find a place where unbalanced_start applies. As an example:: >>> unbalanced_start = ['<div>'] >>> doc = ['<p>', 'Text', '</p>', '<div>', 'More Text', '</div>'] >>> pre, post = doc[:3], doc[3:] >>> pre, post (['<p>', 'Text', '</p>'], ['<div>', 'More Text', '</div>']) >>> locate_unbalanced_start(unbalanced_start, pre, post) >>> pre, post (['<p>', 'Text', '</p>', '<div>'], ['More Text', '</div>']) As you can see, we moved the point so that the dangling <div> that we found will be effectively replaced by the div in the original document. If this doesn't work out, we just throw away unbalanced_start without doing anything. i i s <>Rj Rk t inst dels Unexpected delete tag: %rN( RY t findingRr R t finding_nameRg t nextR] Rp Rs R1 Ru Rf R8 ( RY Rf Rg Rs R R~ R ( ( R Rh \ s, c C s x | p Pn | d } | i d i d } | p Pn | d } | t j p | i d o Pn | i d i d } | d j p | d j o Pn | | j o$ | i | i d | i q Pq Wd S( st like locate_unbalanced_start, except handling end tags and possibly moving the point earlier in the document. i ii s <>/s </R| R} N( R[ R~ Rr R R Rf R R` Rp Rs Ru Rg RI ( R[ Rf Rg Rs R R~ R ( ( R Ri s& R= c B s8 t Z d Z e Z e e e d Z d Z d Z RS( s8 Represents a diffable token, generally a word that is displayed to the user. Opening tags are attached to this token when they are adjacent (pre_tags) and closing tags that follow the word (post_tags). Some exceptions occur when there are empty tags adjacent to a word, so there may be close tags in pre_tags, or open tags in post_tags. We also keep track of whether the word was originally followed by whitespace, even though we do not want to treat the word as equivalent to a similar word that does not have a trailing space.c C se t i | | } | d j o | | _ n g | _ | d j o | | _ n g | _ | | _ | S( N( R t __new__t clsR t objR6 Rx R5 R: ( R R R6 R5 R: R ( ( R R s c C s d t i | | i | i f S( Ns token(%s, %r, %r)( R t __repr__t selfR6 R5 ( R ( ( R R s c C s t | S( N( R R ( R ( ( R R@ s ( R^ R_ Rb R RV Rx R R R@ ( ( ( R R= s t tag_tokenc B s2 t Z d Z e e e d Z d Z d Z RS( s Represents a token that is actually a tag. Currently this is just the <img> tag, which takes up visible space just like a word but is only represented in a document by a tag. c C sM t i | d t | f d | d | d | } | | _ | | _ | | _ | S( Ns %s: %sR6 R5 R: ( R= R R R< t dataR6 R5 R: R Rw t html_repr( R Rw R R R6 R5 R: R ( ( R R s c C s, d | i | i | i | i | i | i f S( NsR tag_token(%s, %s, html_repr=%s, post_tags=%r, pre_tags=%r, trailing_whitespace=%s)( R Rw R R R6 R5 R: ( R ( ( R R s c C s | i S( N( R R ( R ( ( R R@ s ( R^ R_ Rb Rx R R R R@ ( ( ( R R s t href_tokenc B s t Z d Z e Z d Z RS( sh Represents the href in an anchor tag. Unlike other words, we only show the href when it changes. c C s d | S( Ns Link: %s( R ( R ( ( R R@ s ( R^ R_ Rb RP RV R@ ( ( ( R R s c C s4 t | d t } t | d t d | } t | S( sk Parse the given HTML and returns token objects (words with attached tags). This parses only the content of a page; anything in the head is ignored, and the <head> and <body> elements are themselves optional. The content is then parsed by lxml, which ensures the validity of the resulting parsed document (though lxml may make incorrect guesses when the markup is particular bad). <ins> and <del> tags are also eliminated from the document, as that gets confusing. If include_hrefs is true, then the href attribute of <a> tags is included as a special kind of diffable token.t cleanupt skip_tagR N( t parse_htmlR@ RP t body_elt flatten_elR Re t fixup_chunks( R@ R Re R ( ( R R s c C s' | o t | } n t | d t S( s Parses an HTML fragment, returning an lxml element. Note that the HTML will be wrapped in a <div> tag that was not in the original document. If cleanup is true, make sure there's no <head> or <body>, and get rid of any <ins> and <del> tags. t create_parentN( R t cleanup_htmlR@ t fragment_fromstringRP ( R@ R ( ( R R s s <body.*?>s </body.*?>s </?(ins|del).*?>c C sj t i | } | o | | i } n t i | } | o | | i } n t i d | } | S( s This 'cleans' the HTML, meaning that any page structure is removed (only the contents of <body> are used, if there is any <body). Also <ins> and <del> tags are removed. R N( t _body_ret searchR@ t matchRm t _end_body_reRl t _ins_del_ret sub( R@ R ( ( R R s s [ \t\n\r]$c C s- g } d } g } x| D]} t | t o | d d j ov | d } | d } | i d o | d } t } n t } t d | d | d | d | } g } | i | q | d d j o9 | d } t | d | d t } g } | i | q q n t | oY | i d o | d } t } n t } t | d | d | } g } | i | q t | o | i | q t | oM | o | i | q| p t d | | | | f | i i | q d p t q W| p t d d | g Sn | d i i | | S( sM This function takes a list of chunks and produces a list of tokens. i t imgi i R9 iR R6 R: t hrefs4 Weird state, cur_word=%r, result=%r, chunks=%r of %rR N( t tag_accumRx t cur_wordR Re Ro t isinstancet tupleR/ Rw R\ RP R: R R R8 R R t is_wordR= t is_start_tagt is_end_tagR1 R5 RN ( Re R R R Ro Rw R/ R R: ( ( R R , sZ !t paramR t areat brt basefontt inputt baset metat linkt colt addresst blockquotet centert dirt divt dlt fieldsett formt h1t h2t h3t h4t h5t h6t hrt isindext menut noframest noscriptt olt pR? t tablet ult ddt dtt framesett lit tbodyt tdt tfoott tht theadt trc c sc | p< | i d j o d | i d t | f VqC t | Vn | i t j o, | i o! t | o | i o d Sn t | i } x | D] } t i | Vq Wx/ | D]' } x t | d | D] } | Vq Wq W| i d j o/ | i i d o | o d | i d f Vn | p; t | Vt | i } x | D] } t i | VqDWn d S( s Takes an lxml element el, and generates all the text chunks for that tag. Each start tag is a chunk, each word is a chunk, and each end tag is a chunk. If skip_tag is true, then the outermost container tag is not returned (just its contents).R R/ NR R R ( R t elRw t attribt start_tagRt R R. t tailt split_wordst start_wordst wordR R t childR R t itemt gett end_tagt end_words( R R R R R R R R ( ( R R s0 4 * c C sy | p | i o g Sn g } | i i D] } | | d q5 ~ } t i | p | d d | d <n | S( sk Splits some text into words. Includes trailing whitespace (one space) on each word when appropriate. R9 iN( R R R Rr t wt wordst end_whitespace_reR ( R R R R ( ( R R s 1s ^[ \t\n\r]c C sZ d | i d i g } | i i D]) \ } } | d | t i | t f q# ~ f S( s= The text representation of the start tag for a tag. s <%s%s>R s %s="%s"N( R Rw R R R t itemsRs t valueR R RP ( R Rs R R ( ( R R s c C s> | i o t i | i o d } n d } d | i | f S( sg The text representation of an end tag for a tag. Includes trailing whitespace when appropriate. R9 R s </%s>%sN( R R t start_whitespace_reR t extraRw ( R R ( ( R R s c C s | i d S( NRj ( R Rp ( R ( ( R R s c C s | i d S( Ns </( R Rp ( R ( ( R R s c C s | i d o | i d S( NRj s </( R Rp ( R ( ( R R s c C s2 t | d t } t | t | d t } | S( s Given an html string, move any <ins> or <del> tags inside of any block-level elements, e.g. transform <ins><p>word</p></ins> to <p><ins>word</ins></p> R t skip_outerN( R R@ R R t _fixup_ins_del_tagst serialize_html_fragmentRP ( R@ R ( ( R RH s c C s t | t p t d | t i | d d d d } | o8 | | i d d } | | i d } | i Sn | Sd S( s Serialize a single lxml element as HTML. The serialized form includes the elements tail. If skip_outer is true, then don't serialize the outermost tag s3 You should pass in an element, not a string like %rt methodR@ t encodings UTF-8t >i Rj N( R R t basestringR1 t etreet tostringR@ R t findt rfindR ( R R R@ ( ( R R s c C sg x` d d g D]R } xI | i d | D]4 } t | p q' n t | d | | i q' Wq Wd S( s? fixup_ins_del_tags that works on an lxml document in-place R| R} s descendant-or-self::%sRw N( Rw R t xpathR t _contains_block_level_tagt _move_el_inside_blockt drop_tag( R Rw R ( ( R R s c C sR | i t j p | i t j o t Sn x# | D] } t | o t Sq/ q/ Wt S( sP True if the element contains any block-level elements, like <p>, <td>, etc. N( R Rw t block_level_tagst block_level_container_tagsRP R R R ( R R ( ( R R s c C sg xn | D] } t | o Pq q Wd k } t i | } | i | _ d | _ | i t | | g | (d Sx t | D] } t | o` t | | | i oE t i | } | i | _ d | _ | i | i | d | q q~ t i | } | i | | | i | q~ W| i o8 t i | } | i | _ d | _ | i d | n d S( st helper for _fixup_ins_del_tags; actually takes the <ins> etc tags and moves them inside any block-level tags. Ni i ( R R R t sysR t ElementRw t children_tagR Rx RN t listR R t tail_tagRI Ry t child_tagRJ R8 t text_tag( R Rw R R R R R R ( ( R R s: % c C s7 | i } | i p d } | i oZ t | p | | i 7} q | d i o | d i | i 7_ q | i | d _ n | i | } | o | d j o d } n | | d } | d j o* | i o | i | 7_ q| | _ q | i o | i | 7_ q | | _ n | i | | | d +d S( s Removes an element, but merges its contents into its place, e.g., given <p>Hi <i>there!</i></p>, if you remove the <i> element you get <p>Hi there!</p> R ii i N( R t getparentt parentR R R. Ry Rx t previoust getchildren( R R Ry R R ( ( R t _merge_element_contents' s, R c B s t Z d Z d Z d Z RS( st Acts like SequenceMatcher, but tries not to find very small equal blocks amidst large spans of changes i c C s t t | i t | i } t | i | d } t i i | } g } | D]. } | d | j p | d o | | qT qT ~ S( Ni i ( t minR. R R t sizet thresholdt difflibt SequenceMatchert get_matching_blockst actualR R ( R R R R R R ( ( R R Q s !( R^ R_ Rb R R ( ( ( R R I s t __main__( s _diffcommand( R s imgR R R s inputs baseR s linkR ( R R s centers dirR R R R R R R R R R R R R R R R R s preR R ( R R R R R R R R R R (E R t lxmlR t lxml.htmlR R t ret __all__R R R R R- R R7 R R RG R RO RR R] R` t ExceptionRa RT RU RW Rd Rh Ri R R= R R RP R R t compilet It SR R R R R R Rt R R R R R R R R R R RH R R R R R R R R^ t _diffcommandt main(9 R] R Ra Rh R R RR RW R R R R Rt R R R R R R7 R R RG RO R R R R R R R R R R R R R RH R R R` R RU R R R RT R Rd Ri R R R R= R R- R R ( ( R t ? st ( & ' ( 2 ( ; ! "