diff options
Diffstat (limited to 'Objects/codeobject.c')
| -rw-r--r-- | Objects/codeobject.c | 221 |
1 files changed, 76 insertions, 145 deletions
diff --git a/Objects/codeobject.c b/Objects/codeobject.c index e3eccf7..bb938ea 100644 --- a/Objects/codeobject.c +++ b/Objects/codeobject.c @@ -54,7 +54,7 @@ PyCode_New(int argcount, int kwonlyargcount, Py_ssize_t i; /* Check argument types */ - if (argcount < 0 || nlocals < 0 || + if (argcount < 0 || kwonlyargcount < 0 || nlocals < 0 || code == NULL || consts == NULL || !PyTuple_Check(consts) || names == NULL || !PyTuple_Check(names) || @@ -108,10 +108,58 @@ PyCode_New(int argcount, int kwonlyargcount, Py_INCREF(lnotab); co->co_lnotab = lnotab; co->co_zombieframe = NULL; + co->co_weakreflist = NULL; } return co; } +PyCodeObject * +PyCode_NewEmpty(const char *filename, const char *funcname, int firstlineno) +{ + static PyObject *emptystring = NULL; + static PyObject *nulltuple = NULL; + PyObject *filename_ob = NULL; + PyObject *funcname_ob = NULL; + PyCodeObject *result = NULL; + if (emptystring == NULL) { + emptystring = PyBytes_FromString(""); + if (emptystring == NULL) + goto failed; + } + if (nulltuple == NULL) { + nulltuple = PyTuple_New(0); + if (nulltuple == NULL) + goto failed; + } + funcname_ob = PyUnicode_FromString(funcname); + if (funcname_ob == NULL) + goto failed; + filename_ob = PyUnicode_DecodeFSDefault(filename); + if (filename_ob == NULL) + goto failed; + + result = PyCode_New(0, /* argcount */ + 0, /* kwonlyargcount */ + 0, /* nlocals */ + 0, /* stacksize */ + 0, /* flags */ + emptystring, /* code */ + nulltuple, /* consts */ + nulltuple, /* names */ + nulltuple, /* varnames */ + nulltuple, /* freevars */ + nulltuple, /* cellvars */ + filename_ob, /* filename */ + funcname_ob, /* name */ + firstlineno, /* firstlineno */ + emptystring /* lnotab */ + ); + +failed: + Py_XDECREF(funcname_ob); + Py_XDECREF(filename_ob); + return result; +} #define OFF(x) offsetof(PyCodeObject, x) @@ -284,22 +332,28 @@ code_dealloc(PyCodeObject *co) Py_XDECREF(co->co_lnotab); if (co->co_zombieframe != NULL) PyObject_GC_Del(co->co_zombieframe); + if (co->co_weakreflist != NULL) + PyObject_ClearWeakRefs((PyObject*)co); PyObject_DEL(co); } static PyObject * code_repr(PyCodeObject *co) { - int lineno = -1; - char *filename = "???"; - + int lineno; if (co->co_firstlineno != 0) lineno = co->co_firstlineno; - if (co->co_filename && PyUnicode_Check(co->co_filename)) - filename = _PyUnicode_AsString(co->co_filename); - return PyUnicode_FromFormat( - "<code object %.100U at %p, file \"%.300s\", line %d>", - co->co_name, co, filename, lineno); + else + lineno = -1; + if (co->co_filename && PyUnicode_Check(co->co_filename)) { + return PyUnicode_FromFormat( + "<code object %U at %p, file \"%U\", line %d>", + co->co_name, co, co->co_filename, lineno); + } else { + return PyUnicode_FromFormat( + "<code object %U at %p, file ???, line %d>", + co->co_name, co, lineno); + } } static PyObject * @@ -363,10 +417,10 @@ code_richcompare(PyObject *self, PyObject *other, int op) return res; } -static long +static Py_hash_t code_hash(PyCodeObject *co) { - long h, h0, h1, h2, h3, h4, h5, h6; + Py_hash_t h, h0, h1, h2, h3, h4, h5, h6; h0 = PyObject_Hash(co->co_name); if (h0 == -1) return -1; h1 = PyObject_Hash(co->co_code); @@ -415,7 +469,7 @@ PyTypeObject PyCode_Type = { 0, /* tp_traverse */ 0, /* tp_clear */ code_richcompare, /* tp_richcompare */ - 0, /* tp_weaklistoffset */ + offsetof(PyCodeObject, co_weakreflist), /* tp_weaklistoffset */ 0, /* tp_iter */ 0, /* tp_iternext */ 0, /* tp_methods */ @@ -431,54 +485,14 @@ PyTypeObject PyCode_Type = { code_new, /* tp_new */ }; -/* All about c_lnotab. - -c_lnotab is an array of unsigned bytes disguised as a Python string. In -O -mode, SET_LINENO opcodes aren't generated, and bytecode offsets are mapped -to source code line #s (when needed for tracebacks) via c_lnotab instead. -The array is conceptually a list of - (bytecode offset increment, line number increment) -pairs. The details are important and delicate, best illustrated by example: - - byte code offset source code line number - 0 1 - 6 2 - 50 7 - 350 307 - 361 308 - -The first trick is that these numbers aren't stored, only the increments -from one row to the next (this doesn't really work, but it's a start): - - 0, 1, 6, 1, 44, 5, 300, 300, 11, 1 - -The second trick is that an unsigned byte can't hold negative values, or -values larger than 255, so (a) there's a deep assumption that byte code -offsets and their corresponding line #s both increase monotonically, and (b) -if at least one column jumps by more than 255 from one row to the next, more -than one pair is written to the table. In case #b, there's no way to know -from looking at the table later how many were written. That's the delicate -part. A user of c_lnotab desiring to find the source line number -corresponding to a bytecode address A should do something like this - - lineno = addr = 0 - for addr_incr, line_incr in c_lnotab: - addr += addr_incr - if addr > A: - return lineno - lineno += line_incr - -In order for this to work, when the addr field increments by more than 255, -the line # increment in each pair generated must be 0 until the remaining addr -increment is < 256. So, in the example above, com_set_lineno should not (as -was actually done until 2.2) expand 300, 300 to 255, 255, 45, 45, but to -255, 0, 45, 255, 0, 45. +/* Use co_lnotab to compute the line number from a bytecode index, addrq. See + lnotab_notes.txt for the details of the lnotab representation. */ int PyCode_Addr2Line(PyCodeObject *co, int addrq) { - int size = PyBytes_Size(co->co_lnotab) / 2; + Py_ssize_t size = PyBytes_Size(co->co_lnotab) / 2; unsigned char *p = (unsigned char*)PyBytes_AsString(co->co_lnotab); int line = co->co_firstlineno; int addr = 0; @@ -491,87 +505,13 @@ PyCode_Addr2Line(PyCodeObject *co, int addrq) return line; } -/* - Check whether the current instruction is at the start of a line. - - */ - - /* The theory of SET_LINENO-less tracing. - - In a nutshell, we use the co_lnotab field of the code object - to tell when execution has moved onto a different line. - - As mentioned above, the basic idea is so set things up so - that - - *instr_lb <= frame->f_lasti < *instr_ub - - is true so long as execution does not change lines. - - This is all fairly simple. Digging the information out of - co_lnotab takes some work, but is conceptually clear. - - Somewhat harder to explain is why we don't *always* call the - line trace function when the above test fails. - - Consider this code: - - 1: def f(a): - 2: if a: - 3: print 1 - 4: else: - 5: print 2 - - which compiles to this: - - 2 0 LOAD_FAST 0 (a) - 3 JUMP_IF_FALSE 9 (to 15) - 6 POP_TOP - - 3 7 LOAD_CONST 1 (1) - 10 PRINT_ITEM - 11 PRINT_NEWLINE - 12 JUMP_FORWARD 6 (to 21) - >> 15 POP_TOP - - 5 16 LOAD_CONST 2 (2) - 19 PRINT_ITEM - 20 PRINT_NEWLINE - >> 21 LOAD_CONST 0 (None) - 24 RETURN_VALUE - - If 'a' is false, execution will jump to instruction at offset - 15 and the co_lnotab will claim that execution has moved to - line 3. This is at best misleading. In this case we could - associate the POP_TOP with line 4, but that doesn't make - sense in all cases (I think). - - What we do is only call the line trace function if the co_lnotab - indicates we have jumped to the *start* of a line, i.e. if the - current instruction offset matches the offset given for the - start of a line by the co_lnotab. - - This also takes care of the situation where 'a' is true. - Execution will jump from instruction offset 12 to offset 21. - Then the co_lnotab would imply that execution has moved to line - 5, which is again misleading. - - Why do we set f_lineno when tracing? Well, consider the code - above when 'a' is true. If stepping through this with 'n' in - pdb, you would stop at line 1 with a "call" type event, then - line events on lines 2 and 3, then a "return" type event -- but - you would be shown line 5 during this event. This is a change - from the behaviour in 2.2 and before, and I've found it - confusing in practice. By setting and using f_lineno when - tracing, one can report a line number different from that - suggested by f_lasti on this one occasion where it's desirable. - */ - - +/* Update *bounds to describe the first and one-past-the-last instructions in + the same line as lasti. Return the number of that line. */ int -PyCode_CheckLineNumber(PyCodeObject* co, int lasti, PyAddrPair *bounds) +_PyCode_CheckLineNumber(PyCodeObject* co, int lasti, PyAddrPair *bounds) { - int size, addr, line; + Py_ssize_t size; + int addr, line; unsigned char* p; p = (unsigned char*)PyBytes_AS_STRING(co->co_lnotab); @@ -586,11 +526,9 @@ PyCode_CheckLineNumber(PyCodeObject* co, int lasti, PyAddrPair *bounds) instr_lb -- if we stored the matching value of p somwhere we could skip the first while loop. */ - /* see comments in compile.c for the description of + /* See lnotab_notes.txt for the description of co_lnotab. A point to remember: increments to p - should come in pairs -- although we don't care about - the line increments here, treating them as byte - increments gets confusing, to say the least. */ + come in (addr, line) pairs. */ bounds->ap_lower = 0; while (size > 0) { @@ -603,13 +541,6 @@ PyCode_CheckLineNumber(PyCodeObject* co, int lasti, PyAddrPair *bounds) --size; } - /* If lasti and addr don't match exactly, we don't want to - change the lineno slot on the frame or execute a trace - function. Return -1 instead. - */ - if (addr != lasti) - line = -1; - if (size > 0) { while (--size >= 0) { addr += *p++; |