Files
mtgodot-poc/extension/third_party/cpython-2.7.18/Parser/tokenizer.h
T
shenleiandClaude Opus 5 5fad769ee8 port 2P step 1: vendor CPython 2.7.18 as the mtpython static library
The embedded 40250 script layer needs its own interpreter on five platforms.
2.7 is end-of-life, so nothing can be fetched from the target SDKs and the
source is vendored (official 2.7.18 tarball, trimmed to 25MB; Lib/ stays for
step 3's python27.zip).

cpython-2.7.18/CMakeLists.txt builds one `mtpython` static library from exactly
the 133 objects the reference libpython2.7.a contains, off by default behind
-DMTGODOT_EMBED_PYTHON=ON. The source list and the built-in module table
(config/config.c, 39 entries) are shared; pyconfig.h is a probe result and is
not, so each platform keeps its own under config/<platform>/, regenerated by
tools/py_embed/gen_pyconfig.sh and checked against the shared table.

Three vendor patches, documented in docs/THIRD-PARTY.md: configure/configure.ac
learn arm64 on macOS, and posixmodule.c undefines the process-control calls it
hard-defines past pyconfig.h when building for iOS.

macOS (ctest python.embed: every builtin imports, codecs and pickle work off the
vendored Lib/), Android arm64 and iOS arm64 build. Linux needs a Linux host and
Windows needs a MinGW-vs-MSVC decision; both are noted for step 4.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-23 08:27:35 +09:00

71 lines
2.9 KiB
C

#ifndef Py_TOKENIZER_H
#define Py_TOKENIZER_H
#ifdef __cplusplus
extern "C" {
#endif
#include "object.h"
/* Tokenizer interface */
#include "token.h" /* For token types */
#define MAXINDENT 100 /* Max indentation level */
/* 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 */
char *cur; /* Next character in buffer */
char *inp; /* End of data in buffer */
char *end; /* End of input buffer if buf != NULL */
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!!! */
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 */
int decoding_state; /* -1:decoding, 0:init, 1:raw */
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;
const char* input; /* Tokenizer's newline translated copy of the string. */
};
extern struct tok_state *PyTokenizer_FromString(const char *, int);
extern struct tok_state *PyTokenizer_FromFile(FILE *, char *, char *);
extern void PyTokenizer_Free(struct tok_state *);
extern int PyTokenizer_Get(struct tok_state *, char **, char **);
#if defined(PGEN) || defined(Py_USING_UNICODE)
extern char * PyTokenizer_RestoreEncoding(struct tok_state* tok,
int len, int *offset);
#endif
#ifdef __cplusplus
}
#endif
#endif /* !Py_TOKENIZER_H */