o
OjC @ s d Z dZG dd dZe ZdZdZdZdZeeZdZ g dZ
d d
Z dd e fd d
Z er0e Z
dd ZdZdd Zdde fddZdd Zd#ddZd#ddZedkredd dd lZdd lZdd lmZ dd lZe ZdZej dd D ];Z ej e se d qwe!e Z"e"# Z$W d n1 sw Y e d e d ee$ ee$dd ed7 Zqwere d e e d!d" d S d S d S )$a 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.
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.
c @ s e Zd Zedd ZdS ) smartDecodec s, ddl m fdd}t|tj_|| S )N detectc s$ t | tr| S | }| |d S )Nencoding)
isinstancestrdecode)scddr ]/var/www/html/pharmsmart-cdr-gen/venv/lib/python3.10/site-packages/reportlab/lib/rparsexml.py__call__: s z&smartDecode.__call__..__call__)charset_normalizerr staticmethodr __class__r )r
r r r r
r 7 s zsmartDecode.__call__N)__name__
__module__ __qualname__r r r r r r
r 6 s r r ))z<<)z>>)z&&c C s> g }| D ]}d|v rt D ]
\}}|||}q || q|S )Nr ) replacelistreplaceappend) contentListresulteoldnewr r r
unEscapeContentListJ s r" Nc C s$ t | |d\}}|r|d d S |S )z.official interface: discard unused cursor info)entityReplacer r ) parsexml0)xmltextoneOutermostTageoCBr# r cursorr r r
parsexmlSimpleS s r* c C s t | d }t|S )Nr)openreadparsexml)filenamerawr r r
parseFile^ s r1 c C s d}d}|du rM| d|}|dk r|S |d }d}|D ]&}t|}| ||| |krBd}| d|}|dk r>td| |d }q |du rId}|du s|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) textr) prologue_elementsdone openbracketpastfoundr ler r r
skip_prologued s* r< c 1 C s t | } t}d } }}|dur| } |}| d|} | | d | d }
d} | dk rU|durG| |d g}|r=||}||||ft| fS tdt| ||d g } |durft }}
t| |}n| dk rvtdt| dd |
d
kr| | | d d kr| d }| t|}|dk rtd
t| ||d t }| || g}|tt }d} n|
dkr| | | d dkr| d| d }|| k rtdt| ||d |d }| | dkrtdt| ||d d|d fS | d| }|dk }|d }| d }| || }d|vr/|d dkr%|dd }d} | }
|
}|}nGd|v rvd}|sEt|d
dd rGd}|du rv| d|}|d }|dk }| || }|sot|d
dd rqd}|du sL|rtdt| | | d |}| |d dkr|d }|dd }d} | }|
d}|d }|
}|d }
|
}|d }|d d |d< i }} d} t|} | | k rv|| } | d } | } | d dkrtd t| d| dd vr| | krtd t| || } | d } d | | f } d| dd vs| } |
}!|!d }"| dt|" }#|# }#z
|#d }$|#d }%W n td t|#| |!f |$|% krVdksen |$|% krcd!krkn n|#dd }#|#| |< |"}| | k s| dur}| }| durY| d|}&|&|k r|
tkrd} | |d }'t| }|'r| |' ntd"|
t| ||d f | |&d dkr4| d|&}(|(|&k rtd#t| |&|&d | |&d |( })|)
}*|*d }+|
|+kr | d| },t|,
d$}-| d| },t|,
d$}.td%|.|-t|
t|+t| ||d& f | ||& }'|'r-| |' |(d }d} n | ||& }'|'rB| |' t | |&d|d'\}/}|/rT| |/ | dus|rc|rc||}||||f}0|0|fS )(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 r r r
test s
r __main__r r z!!!!! no file at {f!r}zparsing z |t|=z timed at z.2fz secs.)r )%__doc__ simpleparser rM NAMEKEY CONTENTSKEYrQ r3 LENCDATAMARKERrP r r" r* r. r1 verboser< r% r r r r sysosr reportlabr seenargvfpathisfiler r, _fr- r~ r r r r
sZ 3
i