iG d Z dZ dZddlZd Z ej
ddddedd Zdddi fdZ G d d Z e Z d
Z
dZ dZ d Z
ee
Zd Zg d
Zd ZddefdZereZd ZdZd ZddefdZd Zd dZd dZedk( r ed ddl Z ddl Z ddl m Z ddl Z e Z dZ!e jD dd D ]j Z#e jH jK e# s e&d ' e'e# 5 Z(e(jS Z*ddd e&de#d ee* ee*d e!dz
Z!l e!r e&d e e z
d d yyy# e$ r dZY w xY w# 1 sw Y VxY w) at Very simple and fast XML parser, used for intra-paragraph text.
Devised by Aaron Watters in the bad old days before Python had fast
parsers available. Constructs the lightest possible in-memory
representation; parses most files we have seen in pure python very
quickly.
The output structure is the same as the one produced by pyRXP,
our validating C-based parser, which was written later. It will
use pyRXP if available.
This is used to parse intra-paragraph markup.
Example parse::
text in xml
( "this",
{"type": "xml"},
[ "text ",
("b", None, ["in"], None),
" xml"
]
None )
{ 0: "this"
"type": "xml"
1: ["text ",
{0: "b", 1:["in"]},
" xml"]
}
Ie, xml tag translates to a tuple:
(name, dictofattributes, contentlist, miscellaneousinfo)
where miscellaneousinfo can be anything, (but defaults to None)
(with the intention of adding, eg, line number information)
special cases: name of "" means "top level, no containing tag".
Top level parse always looks like this::
("", list, None, None)
contained text of None means
In order to support stuff like::
AT THE MOMENT & ETCETERA ARE IGNORED. THEY MUST BE PROCESSED
IN A POST-PROCESSING STEP.
PROLOGUES ARE NOT UNDERSTOOD. OTHER STUFF IS PROBABLY MISSING.
Nc t | y )N)print)ss W/var/www/html/chat/reports/venv/lib/python3.12/site-packages/reportlab/lib/rparsexml.pywarnCBr > s
a z string input)ErrorOnValidityErrorsNoNoDTDWarningExpandCharacterEntitiesExpandGeneralEntitiesr srcName
ReturnUTF8c b |t _ t j | fi |}|xr |xs dd |gd fS )N ) pyRXP_parsereoCBparse)xmlTextoneOutermostTagr entityReplacer parseOptsps r parsexmlr I s: w 3 3 $1:D!T(::r c e Zd Zed Zy) smartDecodec f ddl m fd}t | t j _ || S )Nr )detectc ` t | t r| S | }| j |d S )Nencoding)
isinstancestrdecode)r cddr s r __call__z&smartDecode.__call__..__call__T s- !C ()C88C
O, ,r )charset_normalizerr staticmethodr __class__r% )r r% r s @r r% zsmartDecode.__call__Q s* - - *6h)? & r N)__name__
__module__ __qualname__r' r% r r r r P s r r r ))z<<)z>>)z&&c g }| D ]7 }d|v r t D ] \ }}|j || } |j | 9 |S )Nr0 ) replacelistreplaceappend) contentListresulteoldnews r unEscapeContentListr: d sS
F
!8 )
(
cIIc3'
(
a
Mr c \ t r t d t | | \ }}|r|d d S |S )z.official interface: discard unused cursor infoz)pyRXP not found, fallback parser disabled)r r ) RequirePyRXP ImportError parsexml0)xmltextr r r r6 cursors r parsexmlSimplerB m s8 EFF GVVay|
r c L t | d j }t | S )Nr)openreadr )filenameraws r parseFilerI z s!
x
"
"
$C C=r c d}d}|r| j d| }|dk r |S |dz }d}|D ]E }t | }| |||z |k( sd}| j d| }|dk rt d|z |dz }G |d}|r|S )zBskip any prologue found after cursor, return index of rest of text)z!DOCTYPEz?xmlz!--Nr. r r r/ zcan't close prologue %r)findlen
ValueError) textrA prologue_elementsdone openbracketpastfoundr7 les r
skip_prologuerU s 4 D
,iiV, q=% M 1}" "AQBDb!1$ 3-!8$%>%BCC " =D ," Mr c t | } t }dx}x}}|| j } |}| j d| } | | dz | dz }
d} | dk r@|!| |d g}|r || }||||ft | fS t dt
| ||dz z g } |t x}}
t | | }nU| dk rt dt
| dd z |
d
k( rj| | | d z d k( r_| d z }| j t | }|dk r t d
t
| ||dz z t }| || g}|t t z }d} n|
dk( rs| | | dz dk( rh| j d| dz }|| k r t dt
| ||dz z |dz }| | dk7 r t dt
| ||dz z d|dz fS | j d| }|dk }|dz }| dz }| || }d|vr%|d dk( r|dd }d} |j }
|
}|}n d|v rpd}|s t |dz j d dz rd}|H| j d| }|dz }|dk }| || }|s t |dz j d dz rd}|H|r t dt
| | | dz z |}| |dz
dk( r |dz
}|dd }d} |j }|j d }|d }|j }|d }
|
}|d }|d d z |d< i x}} d} t | } | | k r|| } | dz } | j } | d dk7 rt d t
| z d| dd vr5| | kD rt d t
| z || } | dz } | d| } d| dd vr5| j } | j }!|!d }"| dt |" }#|#j }# |#d }$|#d }%|$|%cxk( rdk( sn |$|%cxk( rd k( rn n|#dd }#|#| |< |"}| | k r| | }| | j d| }&|&|k rQ
t k( r(d} | |d }'t | }|'rj| j |' nWt d!|
d"t
| ||dz | |&dz dk( r| j d|& }(|(|&k r t d#t
| |&|&dz z | |&dz |( })|)j }*|*d }+
|+k7 ry| d| },t |,j d$ }-| d| },t |,j d$ }.t d%|.d&|-d't
|
d&t
|+ d(t
| ||d)z
| ||& }'|'r| j |' |(dz }d} n=| ||& }'|'r| j |' t | |&d|* \ }/}|/r| j |/ | |r
|r || }||||f}0|0|fS # t d t
|#| |!f z xY w)+zsimple recursive descent xml parser...
return (dictionary, endcharacter)
special case: comment returns (None, endcharacter)Nr. r r zno tags at non-toplevel %s z.non top level entry should be at start tag: %s
z![ r- zunclosed CDATA %sz!- z
text in xml ]]>
just testing brackets feature
r )r r s r testr s
r __main__r r z!!!!! no file at {f!r}zparsing z |t|=z timed at z.2fz secs.)r )+__doc__r= simpleparsepyRXPUr Parserr r r> r rg NAMEKEY CONTENTSKEYrk rL LENCDATAMARKERrj r2 r: rB rI verboserU r? r r r r) sysosr reportlabr seenargvfpathisfiler rE _frF r r, r r r s 5n K 6==./'(01./!' .%&L +,TTV ; m
[!< -.4GZ H 0 #$a*fP+4 ZaL
&C D
XXab\ ww~~a * +a
BGGI
HQEs1vh/ 0 aQ AID
$&*S)01 ! G K\
s *D> &E >E E E