cpython/Parser/tokenizer.h

76 lines
2.6 KiB
C
Raw Normal View History

#ifndef Py_TOKENIZER_H
#define Py_TOKENIZER_H
#ifdef __cplusplus
extern "C" {
#endif
#include "object.h"
1991-02-19 12:39:46 +00:00
1990-10-14 12:07:46 +00:00
/* Tokenizer interface */
#include "token.h" /* For token types */
#define MAXINDENT 100 /* Max indentation level */
enum decoding_state {
STATE_INIT,
STATE_RAW,
STATE_NORMAL, /* have a codec associated with input */
};
1990-10-14 12:07:46 +00:00
/* Tokenizer state */
struct tok_state {
/* Input state; buf <= cur <= inp <= end */
/* NB an entire line is held in the buffer */
char *buf; /* Input buffer, or NULL; malloc'ed if fp != NULL */
1990-10-14 12:07:46 +00:00
char *cur; /* Next character in buffer */
char *inp; /* End of data in buffer */
char *end; /* End of input buffer if buf != NULL */
1994-08-30 08:27:36 +00:00
char *start; /* Start of current token if not NULL */
int done; /* E_OK normally, E_EOF at EOF, otherwise error code */
/* NB If done != E_OK, cur must be == inp!!! */
1990-10-14 12:07:46 +00:00
FILE *fp; /* Rest of input; NULL if tokenizing a string */
int tabsize; /* Tab spacing */
int indent; /* Current indentation index */
int indstack[MAXINDENT]; /* Stack of indents */
int atbol; /* Nonzero if at begin of new line */
int pendin; /* Pending indents (if > 0) or dedents (if < 0) */
char *prompt, *nextprompt; /* For interactive prompting */
int lineno; /* Current line number */
int level; /* () [] {} Parentheses nesting level */
/* Used to allow free continuations inside them */
/* Stuff for checking on different tab sizes */
const char *filename; /* For error messages */
int altwarning; /* Issue warning if alternate tabs don't match */
int alterror; /* Issue error if alternate tabs don't match */
int alttabsize; /* Alternate tab spacing */
int altindstack[MAXINDENT]; /* Stack of alternate indents */
/* Stuff for PEP 0263 */
enum decoding_state decoding_state;
int decoding_erred; /* whether erred in decoding */
int read_coding_spec; /* whether 'coding:...' has been read */
char *encoding;
int cont_line; /* whether we are in a continuation line. */
const char* line_start; /* pointer to start of current line */
#ifndef PGEN
PyObject *decoding_readline; /* codecs.open(...).readline */
PyObject *decoding_buffer;
#endif
const char* enc;
const char* str;
1990-10-14 12:07:46 +00:00
};
extern struct tok_state *PyTokenizer_FromString(const char *);
extern struct tok_state *PyTokenizer_FromFile(FILE *, char*,
char *, char *);
extern void PyTokenizer_Free(struct tok_state *);
extern int PyTokenizer_Get(struct tok_state *, char **, char **);
Merged revisions 57778-58052 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r57820 | georg.brandl | 2007-08-31 08:59:27 +0200 (Fri, 31 Aug 2007) | 2 lines Document new shorthand notation for index entries. ........ r57827 | georg.brandl | 2007-08-31 10:47:51 +0200 (Fri, 31 Aug 2007) | 2 lines Fix subitem markup. ........ r57833 | martin.v.loewis | 2007-08-31 12:01:07 +0200 (Fri, 31 Aug 2007) | 1 line Mark registry components as 64-bit on Win64. ........ r57854 | bill.janssen | 2007-08-31 21:02:23 +0200 (Fri, 31 Aug 2007) | 1 line deprecate use of FakeSocket ........ r57855 | bill.janssen | 2007-08-31 21:02:46 +0200 (Fri, 31 Aug 2007) | 1 line remove mentions of socket.ssl in comments ........ r57856 | bill.janssen | 2007-08-31 21:03:31 +0200 (Fri, 31 Aug 2007) | 1 line remove use of non-existent SSLFakeSocket in apparently untested code ........ r57859 | martin.v.loewis | 2007-09-01 08:36:03 +0200 (Sat, 01 Sep 2007) | 3 lines Bug #1737210: Change Manufacturer of Windows installer to PSF. Will backport to 2.5. ........ r57865 | georg.brandl | 2007-09-01 09:51:24 +0200 (Sat, 01 Sep 2007) | 2 lines Fix RST link (backport from Py3k). ........ r57876 | georg.brandl | 2007-09-01 17:49:49 +0200 (Sat, 01 Sep 2007) | 2 lines Document sets' ">" and "<" operations (backport from py3k). ........ r57878 | skip.montanaro | 2007-09-01 19:40:03 +0200 (Sat, 01 Sep 2007) | 4 lines Added a note and examples to explain that re.split does not split on an empty pattern match. (issue 852532). ........ r57879 | walter.doerwald | 2007-09-01 20:18:09 +0200 (Sat, 01 Sep 2007) | 2 lines Fix wrong function names. ........ r57880 | walter.doerwald | 2007-09-01 20:34:05 +0200 (Sat, 01 Sep 2007) | 2 lines Fix typo. ........ r57889 | andrew.kuchling | 2007-09-01 22:31:59 +0200 (Sat, 01 Sep 2007) | 1 line Markup fix ........ r57892 | andrew.kuchling | 2007-09-01 22:43:36 +0200 (Sat, 01 Sep 2007) | 1 line Add various items ........ r57895 | andrew.kuchling | 2007-09-01 23:17:58 +0200 (Sat, 01 Sep 2007) | 1 line Wording change ........ r57896 | andrew.kuchling | 2007-09-01 23:18:31 +0200 (Sat, 01 Sep 2007) | 1 line Add more items ........ r57904 | ronald.oussoren | 2007-09-02 11:46:07 +0200 (Sun, 02 Sep 2007) | 3 lines Macosx: this patch ensures that the value of MACOSX_DEPLOYMENT_TARGET used by the Makefile is also used at configure-time. ........ r57925 | georg.brandl | 2007-09-03 09:16:46 +0200 (Mon, 03 Sep 2007) | 2 lines Fix #883466: don't allow Unicode as arguments to quopri and uu codecs. ........ r57936 | matthias.klose | 2007-09-04 01:33:04 +0200 (Tue, 04 Sep 2007) | 2 lines - Added support for linking the bsddb module against BerkeleyDB 4.6.x. ........ r57954 | mark.summerfield | 2007-09-04 10:16:15 +0200 (Tue, 04 Sep 2007) | 3 lines Added cross-references plus a note about dict & list shallow copying. ........ r57958 | martin.v.loewis | 2007-09-04 11:51:57 +0200 (Tue, 04 Sep 2007) | 3 lines Document that we rely on the OS to release the crypto context. Fixes #1626801. ........ r57960 | martin.v.loewis | 2007-09-04 15:13:14 +0200 (Tue, 04 Sep 2007) | 3 lines Patch #1388440: Add set_completion_display_matches_hook and get_completion_type to readline. ........ r57961 | martin.v.loewis | 2007-09-04 16:19:28 +0200 (Tue, 04 Sep 2007) | 3 lines Patch #1031213: Decode source line in SyntaxErrors back to its original source encoding. Will backport to 2.5. ........ r57972 | matthias.klose | 2007-09-04 20:17:36 +0200 (Tue, 04 Sep 2007) | 3 lines - Makefile.pre.in(buildbottest): Run an optional script pybuildbot.identify to include some information about the build environment. ........ r57973 | matthias.klose | 2007-09-04 21:05:38 +0200 (Tue, 04 Sep 2007) | 2 lines - Makefile.pre.in(buildbottest): Remove whitespace at eol. ........ r57975 | matthias.klose | 2007-09-04 22:46:02 +0200 (Tue, 04 Sep 2007) | 2 lines - Fix libffi configure for hppa*-*-linux* | parisc*-*-linux*. ........ r57980 | bill.janssen | 2007-09-05 02:46:27 +0200 (Wed, 05 Sep 2007) | 1 line SSL certificate distinguished names should be represented by tuples ........ r57985 | martin.v.loewis | 2007-09-05 08:39:17 +0200 (Wed, 05 Sep 2007) | 3 lines Patch #1105: Explain that one needs to build the solution to get dependencies right. ........ r57987 | armin.rigo | 2007-09-05 09:51:21 +0200 (Wed, 05 Sep 2007) | 4 lines PyDict_GetItem() returns a borrowed reference. There are probably a number of places that are open to attacks such as the following one, in bltinmodule.c:min_max(). ........ r57991 | martin.v.loewis | 2007-09-05 13:47:34 +0200 (Wed, 05 Sep 2007) | 3 lines Patch #786737: Allow building in a tree of symlinks pointing to a readonly source. ........ r57993 | georg.brandl | 2007-09-05 15:36:44 +0200 (Wed, 05 Sep 2007) | 2 lines Backport from Py3k: Bug #1684991: explain lookup semantics for __special__ methods (new-style classes only). ........ r58004 | armin.rigo | 2007-09-06 10:30:51 +0200 (Thu, 06 Sep 2007) | 4 lines Patch #1733973 by peaker: ptrace_enter_call() assumes no exception is currently set. This assumption is broken when throwing into a generator. ........ r58006 | armin.rigo | 2007-09-06 11:30:38 +0200 (Thu, 06 Sep 2007) | 4 lines PyDict_GetItem() returns a borrowed reference. This attack is against ceval.c:IMPORT_NAME, which calls an object (__builtin__.__import__) without holding a reference to it. ........ r58013 | georg.brandl | 2007-09-06 16:49:56 +0200 (Thu, 06 Sep 2007) | 2 lines Backport from 3k: #1116: fix reference to old filename. ........ r58021 | thomas.heller | 2007-09-06 22:26:20 +0200 (Thu, 06 Sep 2007) | 1 line Fix typo: c_float represents to C float type. ........ r58022 | skip.montanaro | 2007-09-07 00:29:06 +0200 (Fri, 07 Sep 2007) | 3 lines If this is correct for py3k branch and it's already in the release25-maint branch, seems like it ought to be on the trunk as well. ........ r58023 | gregory.p.smith | 2007-09-07 00:59:59 +0200 (Fri, 07 Sep 2007) | 4 lines Apply the fix from Issue1112 to make this test more robust and keep windows happy. ........ r58031 | brett.cannon | 2007-09-07 05:17:50 +0200 (Fri, 07 Sep 2007) | 4 lines Make uuid1 and uuid4 tests conditional on whether ctypes can be imported; implementation of either function depends on ctypes but uuid as a whole does not. ........ r58032 | brett.cannon | 2007-09-07 06:18:30 +0200 (Fri, 07 Sep 2007) | 6 lines Fix a crasher where Python code managed to infinitely recurse in C code without ever going back out to Python code in PyObject_Call(). Required introducing a static RuntimeError instance so that normalizing an exception there is no reliance on a recursive call that would put the exception system over the recursion check itself. ........ r58034 | thomas.heller | 2007-09-07 08:32:17 +0200 (Fri, 07 Sep 2007) | 1 line Add a 'c_longdouble' type to the ctypes module. ........ r58035 | thomas.heller | 2007-09-07 11:30:40 +0200 (Fri, 07 Sep 2007) | 1 line Remove unneeded #include. ........ r58036 | thomas.heller | 2007-09-07 11:33:24 +0200 (Fri, 07 Sep 2007) | 6 lines Backport from py3k branch: Add a workaround for a strange bug on win64, when _ctypes is compiled with the SDK compiler. This should fix the failing Lib\ctypes\test\test_as_parameter.py test. ........ r58037 | georg.brandl | 2007-09-07 16:14:40 +0200 (Fri, 07 Sep 2007) | 2 lines Fix a wrong indentation for sublists. ........ r58043 | georg.brandl | 2007-09-07 22:10:49 +0200 (Fri, 07 Sep 2007) | 2 lines #1095: ln -f doesn't work portably, fix in Makefile. ........ r58049 | skip.montanaro | 2007-09-08 02:34:17 +0200 (Sat, 08 Sep 2007) | 1 line be explicit about the actual location of the missing file ........
2007-09-08 17:39:28 +00:00
extern char * PyTokenizer_RestoreEncoding(struct tok_state* tok,
int len, int *offset);
extern char * PyTokenizer_FindEncoding(int);
#ifdef __cplusplus
}
#endif
#endif /* !Py_TOKENIZER_H */