mirror of
https://github.com/python/cpython.git
synced 2025-09-26 18:29:57 +00:00
GH-98831: Remove redundant extract_cases.py script (GH-99065)
Debt I owe from PR GH-98830.
This commit is contained in:
Guido van Rossum
GitHub
parent
b8a9f13abb
commit
916af11a97
3 changed files with 0 additions and 338 deletions
|
|
@ -8,12 +8,6 @@ What's currently here:
|
||||||
- `generate_cases.py`: driver script to read `Python/bytecodes.c` and
|
- `generate_cases.py`: driver script to read `Python/bytecodes.c` and
|
||||||
write `Python/generated_cases.c.h`
|
write `Python/generated_cases.c.h`
|
||||||
|
|
||||||
**Temporarily also:**
|
|
||||||
|
|
||||||
- `extract_cases.py`: script to extract cases from
|
|
||||||
`Python/ceval.c` and write them to `Python/bytecodes.c`
|
|
||||||
- `bytecodes_template.h`: template used by `extract_cases.py`
|
|
||||||
|
|
||||||
The DSL for the instruction definitions in `Python/bytecodes.c` is described
|
The DSL for the instruction definitions in `Python/bytecodes.c` is described
|
||||||
[here](https://github.com/faster-cpython/ideas/blob/main/3.12/interpreter_definition.md).
|
[here](https://github.com/faster-cpython/ideas/blob/main/3.12/interpreter_definition.md).
|
||||||
Note that there is some dummy C code at the top and bottom of the file
|
Note that there is some dummy C code at the top and bottom of the file
|
||||||
|
|
|
||||||
|
|
@ -1,85 +0,0 @@
|
||||||
#include "Python.h"
|
|
||||||
#include "pycore_abstract.h" // _PyIndex_Check()
|
|
||||||
#include "pycore_call.h" // _PyObject_FastCallDictTstate()
|
|
||||||
#include "pycore_ceval.h" // _PyEval_SignalAsyncExc()
|
|
||||||
#include "pycore_code.h"
|
|
||||||
#include "pycore_function.h"
|
|
||||||
#include "pycore_long.h" // _PyLong_GetZero()
|
|
||||||
#include "pycore_object.h" // _PyObject_GC_TRACK()
|
|
||||||
#include "pycore_moduleobject.h" // PyModuleObject
|
|
||||||
#include "pycore_opcode.h" // EXTRA_CASES
|
|
||||||
#include "pycore_pyerrors.h" // _PyErr_Fetch()
|
|
||||||
#include "pycore_pymem.h" // _PyMem_IsPtrFreed()
|
|
||||||
#include "pycore_pystate.h" // _PyInterpreterState_GET()
|
|
||||||
#include "pycore_range.h" // _PyRangeIterObject
|
|
||||||
#include "pycore_sliceobject.h" // _PyBuildSlice_ConsumeRefs
|
|
||||||
#include "pycore_sysmodule.h" // _PySys_Audit()
|
|
||||||
#include "pycore_tuple.h" // _PyTuple_ITEMS()
|
|
||||||
#include "pycore_emscripten_signal.h" // _Py_CHECK_EMSCRIPTEN_SIGNALS
|
|
||||||
|
|
||||||
#include "pycore_dict.h"
|
|
||||||
#include "dictobject.h"
|
|
||||||
#include "pycore_frame.h"
|
|
||||||
#include "opcode.h"
|
|
||||||
#include "pydtrace.h"
|
|
||||||
#include "setobject.h"
|
|
||||||
#include "structmember.h" // struct PyMemberDef, T_OFFSET_EX
|
|
||||||
|
|
||||||
void _PyFloat_ExactDealloc(PyObject *);
|
|
||||||
void _PyUnicode_ExactDealloc(PyObject *);
|
|
||||||
|
|
||||||
#define SET_TOP(v) (stack_pointer[-1] = (v))
|
|
||||||
#define PEEK(n) (stack_pointer[-(n)])
|
|
||||||
|
|
||||||
#define GETLOCAL(i) (frame->localsplus[i])
|
|
||||||
|
|
||||||
#define inst(name) case name:
|
|
||||||
#define family(name) static int family_##name
|
|
||||||
|
|
||||||
#define NAME_ERROR_MSG \
|
|
||||||
"name '%.200s' is not defined"
|
|
||||||
|
|
||||||
typedef struct {
|
|
||||||
PyObject *kwnames;
|
|
||||||
} CallShape;
|
|
||||||
|
|
||||||
static void
|
|
||||||
dummy_func(
|
|
||||||
PyThreadState *tstate,
|
|
||||||
_PyInterpreterFrame *frame,
|
|
||||||
unsigned char opcode,
|
|
||||||
unsigned int oparg,
|
|
||||||
_Py_atomic_int * const eval_breaker,
|
|
||||||
_PyCFrame cframe,
|
|
||||||
PyObject *names,
|
|
||||||
PyObject *consts,
|
|
||||||
_Py_CODEUNIT *next_instr,
|
|
||||||
PyObject **stack_pointer,
|
|
||||||
CallShape call_shape,
|
|
||||||
_Py_CODEUNIT *first_instr,
|
|
||||||
int throwflag,
|
|
||||||
binaryfunc binary_ops[]
|
|
||||||
)
|
|
||||||
{
|
|
||||||
switch (opcode) {
|
|
||||||
|
|
||||||
/* BEWARE!
|
|
||||||
It is essential that any operation that fails must goto error
|
|
||||||
and that all operation that succeed call DISPATCH() ! */
|
|
||||||
|
|
||||||
// BEGIN BYTECODES //
|
|
||||||
// INSERT CASES HERE //
|
|
||||||
// END BYTECODES //
|
|
||||||
|
|
||||||
}
|
|
||||||
error:;
|
|
||||||
exception_unwind:;
|
|
||||||
handle_eval_breaker:;
|
|
||||||
resume_frame:;
|
|
||||||
resume_with_error:;
|
|
||||||
start_frame:;
|
|
||||||
unbound_local_error:;
|
|
||||||
}
|
|
||||||
|
|
||||||
// Families go below this point //
|
|
||||||
|
|
||||||
|
|
@ -1,247 +0,0 @@
|
||||||
"""Extract the main interpreter switch cases."""
|
|
||||||
|
|
||||||
# Reads cases from ceval.c, writes to bytecodes.c.
|
|
||||||
# (This file is not meant to be compiled, but it has a .c extension
|
|
||||||
# so tooling like VS Code can be fooled into thinking it is C code.
|
|
||||||
# This helps editing and browsing the code.)
|
|
||||||
#
|
|
||||||
# The script generate_cases.py regenerates the cases.
|
|
||||||
|
|
||||||
import argparse
|
|
||||||
import difflib
|
|
||||||
import dis
|
|
||||||
import re
|
|
||||||
import sys
|
|
||||||
|
|
||||||
parser = argparse.ArgumentParser()
|
|
||||||
parser.add_argument("-i", "--input", type=str, default="Python/ceval.c")
|
|
||||||
parser.add_argument("-o", "--output", type=str, default="Python/bytecodes.c")
|
|
||||||
parser.add_argument("-t", "--template", type=str, default="Tools/cases_generator/bytecodes_template.c")
|
|
||||||
parser.add_argument("-c", "--compare", action="store_true")
|
|
||||||
parser.add_argument("-q", "--quiet", action="store_true")
|
|
||||||
|
|
||||||
|
|
||||||
inverse_specializations = {
|
|
||||||
specname: familyname
|
|
||||||
for familyname, specnames in dis._specializations.items()
|
|
||||||
for specname in specnames
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
def eopen(filename, mode="r"):
|
|
||||||
if filename == "-":
|
|
||||||
if "r" in mode:
|
|
||||||
return sys.stdin
|
|
||||||
else:
|
|
||||||
return sys.stdout
|
|
||||||
return open(filename, mode)
|
|
||||||
|
|
||||||
|
|
||||||
def leading_whitespace(line):
|
|
||||||
return len(line) - len(line.lstrip())
|
|
||||||
|
|
||||||
|
|
||||||
def extract_opcode_name(line):
|
|
||||||
m = re.match(r"\A\s*TARGET\((\w+)\)\s*{\s*\Z", line)
|
|
||||||
if m:
|
|
||||||
opcode_name = m.group(1)
|
|
||||||
if opcode_name not in dis._all_opmap:
|
|
||||||
raise ValueError(f"error: unknown opcode {opcode_name}")
|
|
||||||
return opcode_name
|
|
||||||
raise ValueError(f"error: no opcode in {line.strip()}")
|
|
||||||
|
|
||||||
|
|
||||||
def figure_stack_effect(opcode_name):
|
|
||||||
# Return (i, diff``) where i is the stack effect for oparg=0
|
|
||||||
# and diff is the increment for oparg=1.
|
|
||||||
# If it is irregular or unknown, raise ValueError.
|
|
||||||
if m := re.match(f"^(\w+)__(\w+)$", opcode_name):
|
|
||||||
# Super-instruction adds effect of both parts
|
|
||||||
first, second = m.groups()
|
|
||||||
se1, incr1 = figure_stack_effect(first)
|
|
||||||
se2, incr2 = figure_stack_effect(second)
|
|
||||||
if incr1 or incr2:
|
|
||||||
raise ValueError(f"irregular stack effect for {opcode_name}")
|
|
||||||
return se1 + se2, 0
|
|
||||||
if opcode_name in inverse_specializations:
|
|
||||||
# Specialized instruction maps to unspecialized instruction
|
|
||||||
opcode_name = inverse_specializations[opcode_name]
|
|
||||||
opcode = dis._all_opmap[opcode_name]
|
|
||||||
if opcode in dis.hasarg:
|
|
||||||
try:
|
|
||||||
se = dis.stack_effect(opcode, 0)
|
|
||||||
except ValueError as err:
|
|
||||||
raise ValueError(f"{err} for {opcode_name}")
|
|
||||||
if dis.stack_effect(opcode, 0, jump=True) != se:
|
|
||||||
raise ValueError(f"{opcode_name} stack effect depends on jump flag")
|
|
||||||
if dis.stack_effect(opcode, 0, jump=False) != se:
|
|
||||||
raise ValueError(f"{opcode_name} stack effect depends on jump flag")
|
|
||||||
for i in range(1, 257):
|
|
||||||
if dis.stack_effect(opcode, i) != se:
|
|
||||||
return figure_variable_stack_effect(opcode_name, opcode, se)
|
|
||||||
else:
|
|
||||||
try:
|
|
||||||
se = dis.stack_effect(opcode)
|
|
||||||
except ValueError as err:
|
|
||||||
raise ValueError(f"{err} for {opcode_name}")
|
|
||||||
if dis.stack_effect(opcode, jump=True) != se:
|
|
||||||
raise ValueError(f"{opcode_name} stack effect depends on jump flag")
|
|
||||||
if dis.stack_effect(opcode, jump=False) != se:
|
|
||||||
raise ValueError(f"{opcode_name} stack effect depends on jump flag")
|
|
||||||
return se, 0
|
|
||||||
|
|
||||||
|
|
||||||
def figure_variable_stack_effect(opcode_name, opcode, se0):
|
|
||||||
# Is it a linear progression?
|
|
||||||
se1 = dis.stack_effect(opcode, 1)
|
|
||||||
diff = se1 - se0
|
|
||||||
for i in range(2, 257):
|
|
||||||
sei = dis.stack_effect(opcode, i)
|
|
||||||
if sei - se0 != diff * i:
|
|
||||||
raise ValueError(f"{opcode_name} has irregular stack effect")
|
|
||||||
# Assume it's okay for larger oparg values too
|
|
||||||
return se0, diff
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
START_MARKER = "/* Start instructions */" # The '{' is on the preceding line.
|
|
||||||
END_MARKER = "/* End regular instructions */"
|
|
||||||
|
|
||||||
def read_cases(f):
|
|
||||||
cases = []
|
|
||||||
case = None
|
|
||||||
started = False
|
|
||||||
# TODO: Count line numbers
|
|
||||||
for line in f:
|
|
||||||
stripped = line.strip()
|
|
||||||
if not started:
|
|
||||||
if stripped == START_MARKER:
|
|
||||||
started = True
|
|
||||||
continue
|
|
||||||
if stripped == END_MARKER:
|
|
||||||
break
|
|
||||||
if stripped.startswith("TARGET("):
|
|
||||||
if case:
|
|
||||||
cases.append(case)
|
|
||||||
indent = " " * leading_whitespace(line)
|
|
||||||
case = ""
|
|
||||||
opcode_name = extract_opcode_name(line)
|
|
||||||
try:
|
|
||||||
se, diff = figure_stack_effect(opcode_name)
|
|
||||||
except ValueError as err:
|
|
||||||
case += f"{indent}// error: {err}\n"
|
|
||||||
case += f"{indent}inst({opcode_name}) {{\n"
|
|
||||||
else:
|
|
||||||
inputs = []
|
|
||||||
outputs = []
|
|
||||||
if se > 0:
|
|
||||||
for i in range(se):
|
|
||||||
outputs.append(f"__{i}")
|
|
||||||
elif se < 0:
|
|
||||||
for i in range(-se):
|
|
||||||
inputs.append(f"__{i}")
|
|
||||||
if diff > 0:
|
|
||||||
if diff == 1:
|
|
||||||
outputs.append(f"__array[oparg]")
|
|
||||||
else:
|
|
||||||
outputs.append(f"__array[oparg*{diff}]")
|
|
||||||
elif diff < 0:
|
|
||||||
if diff == -1:
|
|
||||||
inputs.append(f"__array[oparg]")
|
|
||||||
else:
|
|
||||||
inputs.append(f"__array[oparg*{-diff}]")
|
|
||||||
input = ", ".join(inputs)
|
|
||||||
output = ", ".join(outputs)
|
|
||||||
case += f"{indent}// stack effect: ({input} -- {output})\n"
|
|
||||||
case += f"{indent}inst({opcode_name}) {{\n"
|
|
||||||
else:
|
|
||||||
if case:
|
|
||||||
case += line
|
|
||||||
if case:
|
|
||||||
cases.append(case)
|
|
||||||
return cases
|
|
||||||
|
|
||||||
|
|
||||||
def write_cases(f, cases):
|
|
||||||
for case in cases:
|
|
||||||
caselines = case.splitlines()
|
|
||||||
while caselines[-1].strip() == "":
|
|
||||||
caselines.pop()
|
|
||||||
if caselines[-1].strip() == "}":
|
|
||||||
caselines.pop()
|
|
||||||
else:
|
|
||||||
raise ValueError("case does not end with '}'")
|
|
||||||
if caselines[-1].strip() == "DISPATCH();":
|
|
||||||
caselines.pop()
|
|
||||||
caselines.append(" }")
|
|
||||||
case = "\n".join(caselines)
|
|
||||||
print(case + "\n", file=f)
|
|
||||||
|
|
||||||
|
|
||||||
def write_families(f):
|
|
||||||
for opcode, specializations in dis._specializations.items():
|
|
||||||
all = [opcode] + specializations
|
|
||||||
if len(all) <= 3:
|
|
||||||
members = ', '.join(all)
|
|
||||||
print(f"family({opcode.lower()}) = {{ {members} }};", file=f)
|
|
||||||
else:
|
|
||||||
print(f"family({opcode.lower()}) = {{", file=f)
|
|
||||||
for i in range(0, len(all), 3):
|
|
||||||
members = ', '.join(all[i:i+3])
|
|
||||||
if i+3 < len(all):
|
|
||||||
print(f" {members},", file=f)
|
|
||||||
else:
|
|
||||||
print(f" {members} }};", file=f)
|
|
||||||
|
|
||||||
|
|
||||||
def compare(oldfile, newfile, quiet=False):
|
|
||||||
with open(oldfile) as f:
|
|
||||||
oldlines = f.readlines()
|
|
||||||
for top, line in enumerate(oldlines):
|
|
||||||
if line.strip() == START_MARKER:
|
|
||||||
break
|
|
||||||
else:
|
|
||||||
print(f"No start marker found in {oldfile}", file=sys.stderr)
|
|
||||||
return
|
|
||||||
del oldlines[:top]
|
|
||||||
for bottom, line in enumerate(oldlines):
|
|
||||||
if line.strip() == END_MARKER:
|
|
||||||
break
|
|
||||||
else:
|
|
||||||
print(f"No end marker found in {oldfile}", file=sys.stderr)
|
|
||||||
return
|
|
||||||
del oldlines[bottom:]
|
|
||||||
if not quiet:
|
|
||||||
print(
|
|
||||||
f"// {oldfile} has {len(oldlines)} lines after stripping top/bottom",
|
|
||||||
file=sys.stderr,
|
|
||||||
)
|
|
||||||
with open(newfile) as f:
|
|
||||||
newlines = f.readlines()
|
|
||||||
if not quiet:
|
|
||||||
print(f"// {newfile} has {len(newlines)} lines", file=sys.stderr)
|
|
||||||
for line in difflib.unified_diff(oldlines, newlines, fromfile=oldfile, tofile=newfile):
|
|
||||||
sys.stdout.write(line)
|
|
||||||
|
|
||||||
|
|
||||||
def main():
|
|
||||||
args = parser.parse_args()
|
|
||||||
with eopen(args.input) as f:
|
|
||||||
cases = read_cases(f)
|
|
||||||
with open(args.template) as f:
|
|
||||||
prolog, epilog = f.read().split("// INSERT CASES HERE //", 1)
|
|
||||||
if not args.quiet:
|
|
||||||
print(f"// Read {len(cases)} cases from {args.input}", file=sys.stderr)
|
|
||||||
with eopen(args.output, "w") as f:
|
|
||||||
f.write(prolog)
|
|
||||||
write_cases(f, cases)
|
|
||||||
f.write(epilog)
|
|
||||||
write_families(f)
|
|
||||||
if not args.quiet:
|
|
||||||
print(f"// Wrote {len(cases)} cases to {args.output}", file=sys.stderr)
|
|
||||||
if args.compare:
|
|
||||||
compare(args.input, args.output, args.quiet)
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
main()
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue