gh-112301: Enable warning emitting options and ignore warnings in CI (#123020)

Co-authored-by: Hugo van Kemenade <1324225+hugovk@users.noreply.github.com>
Co-authored-by: blurb-it[bot] <43283697+blurb-it[bot]@users.noreply.github.com>

3 files changed, 548 insertions, 85 deletions

diff --git a/Tools/build/.warningignore_macos b/Tools/build/.warningignore_macos
index 67f5011..fffb828 100644
--- a/Tools/build/.warningignore_macos
+++ b/Tools/build/.warningignore_macos
@@ -3,3 +3,230 @@
 # Keep lines sorted lexicographically to help avoid merge conflicts.
 # Format example:
 # /path/to/file (number of warnings in file)
+Include/internal/mimalloc/mimalloc/internal.h 4
+Include/internal/pycore_backoff.h 1
+Include/internal/pycore_dict.h 2
+Include/internal/pycore_gc.h 1
+Include/internal/pycore_long.h 2
+Include/internal/pycore_object.h 4
+Modules/_asynciomodule.c 3
+Modules/_bisectmodule.c 2
+Modules/_bz2module.c 5
+Modules/_collectionsmodule.c 2
+Modules/_csv.c 3
+Modules/_ctypes/_ctypes.c 37
+Modules/_ctypes/_ctypes_test_generated.c.h 141
+Modules/_ctypes/callbacks.c 6
+Modules/_ctypes/callproc.c 15
+Modules/_ctypes/cfield.c 59
+Modules/_ctypes/malloc_closure.c 3
+Modules/_ctypes/stgdict.c 17
+Modules/_cursesmodule.c 24
+Modules/_datetimemodule.c 28
+Modules/_dbmmodule.c 8
+Modules/_decimal/_decimal.c 15
+Modules/_elementtree.c 42
+Modules/_functoolsmodule.c 6
+Modules/_gdbmmodule.c 5
+Modules/_hacl/Hacl_Hash_Blake2b_Simd256.c 84
+Modules/_hacl/Hacl_Hash_Blake2s_Simd128.c 84
+Modules/_hacl/include/krml/FStar_UInt_8_16_32_64.h 24
+Modules/_hashopenssl.c 16
+Modules/_interpchannelsmodule.c 1
+Modules/_interpqueuesmodule.c 1
+Modules/_io/_iomodule.c 1
+Modules/_io/bufferedio.c 4
+Modules/_io/bytesio.c 11
+Modules/_io/fileio.c 9
+Modules/_io/stringio.c 8
+Modules/_io/textio.c 11
+Modules/_json.c 19
+Modules/_localemodule.c 3
+Modules/_lzmamodule.c 10
+Modules/_multiprocessing/semaphore.c 2
+Modules/_operator.c 5
+Modules/_pickle.c 71
+Modules/_posixsubprocess.c 8
+Modules/_queuemodule.c 4
+Modules/_randommodule.c 3
+Modules/_scproxy.c 3
+Modules/_sqlite/connection.c 4
+Modules/_sqlite/cursor.c 3
+Modules/_sqlite/module.c 2
+Modules/_sre/sre.c 18
+Modules/_sre/sre_lib.h 62
+Modules/_ssl.c 29
+Modules/_struct.c 1
+Modules/_testbuffer.c 22
+Modules/_testcapi/heaptype.c 1
+Modules/_testcapi/long.c 2
+Modules/_testcapi/mem.c 2
+Modules/_testcapi/monitoring.c 3
+Modules/_testcapi/pyatomic.c 1
+Modules/_testcapi/unicode.c 2
+Modules/_testcapi/vectorcall.c 3
+Modules/_testcapi/watchers.c 3
+Modules/_testcapimodule.c 3
+Modules/_testclinic.c 14
+Modules/_testexternalinspection.c 8
+Modules/_testinternalcapi.c 8
+Modules/_testinternalcapi/pytime.c 8
+Modules/_testinternalcapi/test_critical_sections.c 1
+Modules/_testinternalcapi/test_lock.c 2
+Modules/_testlimitedcapi/heaptype_relative.c 4
+Modules/_testlimitedcapi/object.c 2
+Modules/_testlimitedcapi/unicode.c 2
+Modules/_threadmodule.c 2
+Modules/_tkinter.c 6
+Modules/_xxtestfuzz/_xxtestfuzz.c 1
+Modules/_xxtestfuzz/fuzzer.c 11
+Modules/_zoneinfo.c 14
+Modules/arraymodule.c 32
+Modules/atexitmodule.c 1
+Modules/binascii.c 206
+Modules/blake2module.c 6
+Modules/cjkcodecs/_codecs_cn.c 1
+Modules/cjkcodecs/_codecs_iso2022.c 2
+Modules/cjkcodecs/_codecs_jp.c 14
+Modules/cjkcodecs/_codecs_kr.c 3
+Modules/cjkcodecs/cjkcodecs.h 1
+Modules/cjkcodecs/multibytecodec.c 2
+Modules/clinic/_testclinic.c.h 1
+Modules/clinic/arraymodule.c.h 1
+Modules/clinic/unicodedata.c.h 10
+Modules/cmathmodule.c 1
+Modules/expat/siphash.h 8
+Modules/expat/xmlparse.c 45
+Modules/expat/xmltok.c 17
+Modules/expat/xmltok_impl.c 34
+Modules/faulthandler.c 3
+Modules/fcntlmodule.c 1
+Modules/getpath.c 7
+Modules/grpmodule.c 4
+Modules/itertoolsmodule.c 7
+Modules/main.c 2
+Modules/mathmodule.c 15
+Modules/mmapmodule.c 20
+Modules/posixmodule.c 67
+Modules/pwdmodule.c 4
+Modules/pyexpat.c 20
+Modules/readline.c 1
+Modules/resource.c 3
+Modules/rotatingtree.c 1
+Modules/selectmodule.c 6
+Modules/sha3module.c 4
+Modules/signalmodule.c 1
+Modules/socketmodule.c 44
+Modules/syslogmodule.c 3
+Modules/timemodule.c 4
+Modules/unicodedata.c 28
+Modules/unicodedata_db.h 1
+Modules/xxsubtype.c 2
+Modules/zlibmodule.c 16
+Objects/abstract.c 2
+Objects/bytearrayobject.c 34
+Objects/bytes_methods.c 9
+Objects/bytesobject.c 35
+Objects/call.c 13
+Objects/classobject.c 4
+Objects/codeobject.c 15
+Objects/descrobject.c 2
+Objects/dictobject.c 28
+Objects/fileobject.c 3
+Objects/floatobject.c 30
+Objects/frameobject.c 19
+Objects/funcobject.c 1
+Objects/genobject.c 5
+Objects/listobject.c 43
+Objects/longobject.c 46
+Objects/memoryobject.c 6
+Objects/methodobject.c 1
+Objects/mimalloc/alloc.c 6
+Objects/mimalloc/arena.c 6
+Objects/mimalloc/heap.c 1
+Objects/mimalloc/init.c 2
+Objects/mimalloc/options.c 1
+Objects/mimalloc/os.c 4
+Objects/mimalloc/page-queue.c 2
+Objects/mimalloc/page.c 1
+Objects/mimalloc/prim/osx/../unix/prim.c 2
+Objects/mimalloc/random.c 1
+Objects/mimalloc/segment.c 11
+Objects/mimalloc/stats.c 1
+Objects/moduleobject.c 2
+Objects/object.c 1
+Objects/obmalloc.c 6
+Objects/odictobject.c 3
+Objects/rangeobject.c 10
+Objects/setobject.c 13
+Objects/sliceobject.c 4
+Objects/stringlib/codecs.h 26
+Objects/stringlib/eq.h 1
+Objects/stringlib/fastsearch.h 14
+Objects/stringlib/join.h 1
+Objects/stringlib/replace.h 4
+Objects/stringlib/repr.h 21
+Objects/stringlib/transmogrify.h 5
+Objects/structseq.c 14
+Objects/tupleobject.c 10
+Objects/typeobject.c 17
+Objects/unicodectype.c 7
+Objects/unicodeobject.c 113
+Parser/action_helpers.c 4
+Parser/lexer/buffer.c 1
+Parser/lexer/lexer.c 12
+Parser/parser.c 116
+Parser/pegen.c 7
+Parser/string_parser.c 7
+Parser/tokenizer/file_tokenizer.c 8
+Parser/tokenizer/helpers.c 7
+Parser/tokenizer/readline_tokenizer.c 3
+Programs/_freeze_module.c 1
+Python/Python-ast.c 15
+Python/asdl.c 3
+Python/assemble.c 7
+Python/ast_opt.c 7
+Python/bltinmodule.c 9
+Python/bootstrap_hash.c 4
+Python/ceval.c 8
+Python/ceval_gil.c 2
+Python/codecs.c 32
+Python/codegen.c 6
+Python/compile.c 2
+Python/context.c 1
+Python/crossinterp.c 2
+Python/crossinterp_data_lookup.h 1
+Python/dtoa.c 34
+Python/errors.c 1
+Python/fileutils.c 7
+Python/flowgraph.c 8
+Python/formatter_unicode.c 7
+Python/frame.c 4
+Python/gc.c 8
+Python/generated_cases.c.h 35
+Python/getargs.c 11
+Python/import.c 5
+Python/initconfig.c 11
+Python/instrumentation.c 31
+Python/intrinsics.c 1
+Python/legacy_tracing.c 3
+Python/lock.c 4
+Python/marshal.c 11
+Python/modsupport.c 3
+Python/mystrtoul.c 4
+Python/pathconfig.c 1
+Python/preconfig.c 2
+Python/pyarena.c 1
+Python/pyhash.c 2
+Python/pylifecycle.c 7
+Python/pystate.c 6
+Python/pystrhex.c 19
+Python/pystrtod.c 3
+Python/qsbr.c 2
+Python/specialize.c 10
+Python/suggestions.c 12
+Python/symtable.c 18
+Python/sysmodule.c 2
+Python/thread_pthread.h 1
+Python/traceback.c 6
+Python/tracemalloc.c 6
diff --git a/Tools/build/.warningignore_ubuntu b/Tools/build/.warningignore_ubuntu
index 469c727..e98305e 100644
--- a/Tools/build/.warningignore_ubuntu
+++ b/Tools/build/.warningignore_ubuntu
@@ -3,3 +3,263 @@
 # Keep lines sorted lexicographically to help avoid merge conflicts.
 # Format example:
 # /path/to/file (number of warnings in file)
+/home/runner/work/cpython/cpython/multissl/openssl/3.0.15/include/openssl/evp.h 2
+/home/runner/work/cpython/cpython/multissl/openssl/3.0.15/include/openssl/ssl.h 4
+/usr/include/tcl8.6/tclTomMathDecls.h 1
+Include/cpython/bytearrayobject.h 1
+Include/cpython/bytesobject.h 3
+Include/cpython/dictobject.h 2
+Include/cpython/listobject.h 1
+Include/cpython/pyctype.h 2
+Include/cpython/tupleobject.h 1
+Include/cpython/unicodeobject.h 7
+Include/internal/mimalloc/mimalloc/internal.h 4
+Include/internal/mimalloc/mimalloc/types.h 2
+Include/internal/pycore_asdl.h 1
+Include/internal/pycore_backoff.h 3
+Include/internal/pycore_blocks_output_buffer.h 1
+Include/internal/pycore_dict.h 2
+Include/internal/pycore_gc.h 1
+Include/internal/pycore_gc.h 1
+Include/internal/pycore_interp.h 1
+Include/internal/pycore_list.h 1
+Include/internal/pycore_long.h 3
+Include/internal/pycore_object.h 4
+Include/internal/pycore_obmalloc.h 1
+Include/internal/pycore_pymath.h 1
+Include/internal/pycore_runtime_init.h 1
+Include/longobject.h 1
+Include/object.h 4
+Include/opcode_ids.h 1
+Include/pymacro.h 4
+Include/pymath.h 1
+Include/pymem.h 2
+Include/pyport.h 2
+Modules/_asynciomodule.c 3
+Modules/_bisectmodule.c 4
+Modules/_bz2module.c 5
+Modules/_collectionsmodule.c 2
+Modules/_csv.c 2
+Modules/_ctypes/_ctypes.c 53
+Modules/_ctypes/_ctypes_test.c 7
+Modules/_ctypes/_ctypes_test_generated.c.h 2
+Modules/_ctypes/callbacks.c 3
+Modules/_ctypes/callproc.c 13
+Modules/_ctypes/cfield.c 33
+Modules/_ctypes/stgdict.c 17
+Modules/_cursesmodule.c 27
+Modules/_datetimemodule.c 38
+Modules/_datetimemodule.c 38
+Modules/_dbmmodule.c 7
+Modules/_decimal/_decimal.c 19
+Modules/_elementtree.c 37
+Modules/_functoolsmodule.c 6
+Modules/_gdbmmodule.c 4
+Modules/_hacl/Hacl_Hash_Blake2b_Simd256.c 84
+Modules/_hacl/Hacl_Hash_Blake2b_Simd256.c 84
+Modules/_hacl/Hacl_Hash_Blake2s_Simd128.c 84
+Modules/_hacl/Hacl_Hash_Blake2s_Simd128.c 84
+Modules/_hacl/include/krml/FStar_UInt_8_16_32_64.h 4
+Modules/_hashopenssl.c 13
+Modules/_io/_iomodule.c 1
+Modules/_io/bufferedio.c 15
+Modules/_io/bytesio.c 14
+Modules/_io/fileio.c 9
+Modules/_io/stringio.c 8
+Modules/_io/textio.c 17
+Modules/_json.c 19
+Modules/_localemodule.c 2
+Modules/_lsprof.c 5
+Modules/_lzmamodule.c 6
+Modules/_multiprocessing/posixshmem.c 1
+Modules/_multiprocessing/semaphore.c 1
+Modules/_operator.c 5
+Modules/_pickle.c 73
+Modules/_posixsubprocess.c 11
+Modules/_queuemodule.c 4
+Modules/_randommodule.c 3
+Modules/_sqlite/connection.c 5
+Modules/_sqlite/cursor.c 3
+Modules/_sqlite/module.c 2
+Modules/_sre/sre.c 14
+Modules/_sre/sre_lib.h 25
+Modules/_ssl.c 26
+Modules/_struct.c 3
+Modules/_testbuffer.c 27
+Modules/_testcapi/bytes.c 1
+Modules/_testcapi/heaptype.c 1
+Modules/_testcapi/long.c 2
+Modules/_testcapi/mem.c 2
+Modules/_testcapi/monitoring.c 3
+Modules/_testcapi/pyatomic.c 4
+Modules/_testcapi/pyatomic.c 4
+Modules/_testcapi/unicode.c 1
+Modules/_testcapi/vectorcall.c 3
+Modules/_testcapi/watchers.c 3
+Modules/_testcapimodule.c 1
+Modules/_testclinic.c 14
+Modules/_testclinic.c 14
+Modules/_testexternalinspection.c 7
+Modules/_testinternalcapi.c 10
+Modules/_testinternalcapi/test_critical_sections.c 1
+Modules/_testinternalcapi/test_lock.c 4
+Modules/_testlimitedcapi/heaptype_relative.c 3
+Modules/_testlimitedcapi/object.c 2
+Modules/_testlimitedcapi/unicode.c 1
+Modules/_testmultiphase.c 1
+Modules/_tkinter.c 8
+Modules/_xxtestfuzz/_xxtestfuzz.c 1
+Modules/_xxtestfuzz/fuzzer.c 13
+Modules/_zoneinfo.c 17
+Modules/arraymodule.c 48
+Modules/binascii.c 208
+Modules/blake2module.c 8
+Modules/cjkcodecs/_codecs_iso2022.c 1
+Modules/cjkcodecs/_codecs_jp.c 17
+Modules/cjkcodecs/_codecs_kr.c 7
+Modules/cjkcodecs/alg_jisx0201.h 2
+Modules/cjkcodecs/cjkcodecs.h 1
+Modules/cjkcodecs/multibytecodec.c 12
+Modules/expat/pyexpatns.h 3
+Modules/expat/siphash.h 1
+Modules/expat/xmlparse.c 43
+Modules/expat/xmltok.c 15
+Modules/expat/xmltok.c 15
+Modules/expat/xmltok_impl.c 8
+Modules/faulthandler.c 5
+Modules/fcntlmodule.c 6
+Modules/getpath.c 7
+Modules/grpmodule.c 4
+Modules/itertoolsmodule.c 4
+Modules/main.c 2
+Modules/mathmodule.c 14
+Modules/mmapmodule.c 22
+Modules/mmapmodule.c 22
+Modules/posixmodule.c 79
+Modules/pwdmodule.c 4
+Modules/pyexpat.c 10
+Modules/readline.c 1
+Modules/resource.c 4
+Modules/rotatingtree.c 2
+Modules/selectmodule.c 1
+Modules/sha3module.c 4
+Modules/signalmodule.c 3
+Modules/socketmodule.c 75
+Modules/syslogmodule.c 3
+Modules/termios.c 1
+Modules/timemodule.c 10
+Modules/unicodedata.c 24
+Modules/unicodedata_db.h 1
+Modules/zlibmodule.c 24
+Objects/abstract.c 6
+Objects/bytearrayobject.c 42
+Objects/bytes_methods.c 4
+Objects/bytesobject.c 45
+Objects/call.c 12
+Objects/classobject.c 4
+Objects/codeobject.c 19
+Objects/descrobject.c 2
+Objects/dictobject.c 31
+Objects/fileobject.c 3
+Objects/floatobject.c 10
+Objects/frameobject.c 16
+Objects/funcobject.c 1
+Objects/genobject.c 3
+Objects/listobject.c 38
+Objects/longobject.c 47
+Objects/memoryobject.c 12
+Objects/methodobject.c 1
+Objects/mimalloc/alloc.c 6
+Objects/mimalloc/arena.c 6
+Objects/mimalloc/heap.c 2
+Objects/mimalloc/init.c 2
+Objects/mimalloc/options.c 4
+Objects/mimalloc/os.c 4
+Objects/mimalloc/page-queue.c 2
+Objects/mimalloc/page.c 2
+Objects/mimalloc/prim/unix/prim.c 6
+Objects/mimalloc/random.c 1
+Objects/mimalloc/segment.c 11
+Objects/mimalloc/stats.c 5
+Objects/moduleobject.c 4
+Objects/object.c 1
+Objects/obmalloc.c 6
+Objects/odictobject.c 6
+Objects/rangeobject.c 10
+Objects/setobject.c 13
+Objects/sliceobject.c 2
+Objects/stringlib/codecs.h 12
+Objects/stringlib/eq.h 1
+Objects/stringlib/fastsearch.h 8
+Objects/stringlib/join.h 3
+Objects/stringlib/replace.h 4
+Objects/stringlib/repr.h 21
+Objects/stringlib/transmogrify.h 26
+Objects/structseq.c 10
+Objects/tupleobject.c 8
+Objects/typeobject.c 38
+Objects/unicodectype.c 7
+Objects/unicodeobject.c 135
+Parser/action_helpers.c 3
+Parser/lexer/buffer.c 1
+Parser/lexer/lexer.c 14
+Parser/parser.c 116
+Parser/pegen.c 8
+Parser/string_parser.c 7
+Parser/tokenizer/file_tokenizer.c 9
+Parser/tokenizer/helpers.c 7
+Parser/tokenizer/readline_tokenizer.c 4
+Python/assemble.c 11
+Python/ast_opt.c 5
+Python/bltinmodule.c 8
+Python/bootstrap_hash.c 7
+Python/ceval.c 8
+Python/ceval_gil.c 2
+Python/codecs.c 28
+Python/codegen.c 6
+Python/compile.c 2
+Python/context.c 1
+Python/crossinterp.c 2
+Python/crossinterp_data_lookup.h 1
+Python/dtoa.c 30
+Python/errors.c 1
+Python/fileutils.c 11
+Python/flowgraph.c 7
+Python/formatter_unicode.c 6
+Python/frame.c 3
+Python/gc.c 9
+Python/gc.c 9
+Python/generated_cases.c.h 27
+Python/generated_cases.c.h 27
+Python/getargs.c 7
+Python/hashtable.c 1
+Python/import.c 6
+Python/import.c 7
+Python/initconfig.c 11
+Python/instrumentation.c 43
+Python/intrinsics.c 1
+Python/legacy_tracing.c 3
+Python/lock.c 4
+Python/marshal.c 16
+Python/modsupport.c 3
+Python/mystrtoul.c 4
+Python/pathconfig.c 1
+Python/perf_jit_trampoline.c 32
+Python/perf_trampoline.c 12
+Python/preconfig.c 2
+Python/pyarena.c 1
+Python/pyhash.c 4
+Python/pylifecycle.c 3
+Python/pystate.c 4
+Python/pystrhex.c 15
+Python/pystrtod.c 12
+Python/pytime.c 2
+Python/qsbr.c 2
+Python/specialize.c 9
+Python/suggestions.c 12
+Python/symtable.c 15
+Python/sysmodule.c 2
+Python/thread.c 1
+Python/thread_pthread.h 6
+Python/traceback.c 6
+Python/tracemalloc.c 6
diff --git a/Tools/build/check_warnings.py b/Tools/build/check_warnings.py
index 1ed8344..a9d0c1e 100644
--- a/Tools/build/check_warnings.py
+++ b/Tools/build/check_warnings.py
@@ -1,38 +1,49 @@
 """
-Parses compiler output with -fdiagnostics-format=json and checks that warnings
+Parses compiler output from Clang or GCC and checks that warnings
 exist only in files that are expected to have warnings.
 """
 
 import argparse
 from collections import defaultdict
-import json
 import re
 import sys
 from pathlib import Path
 from typing import NamedTuple
 
+
 class FileWarnings(NamedTuple):
     name: str
     count: int
 
 
-def extract_warnings_from_compiler_output_clang(
+def extract_warnings_from_compiler_output(
     compiler_output: str,
+    compiler_output_type: str,
+    path_prefix: str = "",
 ) -> list[dict]:
     """
-    Extracts warnings from the compiler output when using clang
+    Extracts warnings from the compiler output based on compiler
+    output type. Removes path prefix from file paths if provided.
+    Compatible with GCC and Clang compiler output.
     """
-    # Regex to find warnings in the compiler output
-    clang_warning_regex = re.compile(
-        r"(?P<file>.*):(?P<line>\d+):(?P<column>\d+): warning: "
-        r"(?P<message>.*) (?P<option>\[-[^\]]+\])$"
-    )
+    # Choose pattern and compile regex for particular compiler output
+    if compiler_output_type == "gcc":
+        regex_pattern = (
+            r"(?P<file>.*):(?P<line>\d+):(?P<column>\d+): warning: "
+            r"(?P<message>.*?)(?: (?P<option>\[-[^\]]+\]))?$"
+        )
+    elif compiler_output_type == "clang":
+        regex_pattern = (
+            r"(?P<file>.*):(?P<line>\d+):(?P<column>\d+): warning: "
+            r"(?P<message>.*) (?P<option>\[-[^\]]+\])$"
+        )
+    compiled_regex = re.compile(regex_pattern)
     compiler_warnings = []
     for line in compiler_output.splitlines():
-        if match := clang_warning_regex.match(line):
+        if match := compiled_regex.match(line):
             compiler_warnings.append(
                 {
-                    "file": match.group("file"),
+                    "file": match.group("file").removeprefix(path_prefix),
                     "line": match.group("line"),
                     "column": match.group("column"),
                     "message": match.group("message"),
@@ -43,63 +54,11 @@ def extract_warnings_from_compiler_output_clang(
     return compiler_warnings
 
 
-def extract_warnings_from_compiler_output_json(
-    compiler_output: str,
-) -> list[dict]:
-    """
-    Extracts warnings from the compiler output when using
-    -fdiagnostics-format=json.
-
-    Compiler output as a whole is not a valid json document,
-    but includes many json objects and may include other output
-    that is not json.
-    """
-    # Regex to find json arrays at the top level of the file
-    # in the compiler output
-    json_arrays = re.findall(r"\[(?:[^[\]]|\[[^]]*])*]", compiler_output)
-    compiler_warnings = []
-    for array in json_arrays:
-        try:
-            json_data = json.loads(array)
-            json_objects_in_array = [entry for entry in json_data]
-            warning_list = [
-                entry
-                for entry in json_objects_in_array
-                if entry.get("kind") == "warning"
-            ]
-            for warning in warning_list:
-                locations = warning["locations"]
-                for location in locations:
-                    for key in ["caret", "start", "end"]:
-                        if key in location:
-                            compiler_warnings.append(
-                                {
-                                    # Remove leading current directory if present
-                                    "file": location[key]["file"].lstrip("./"),
-                                    "line": location[key]["line"],
-                                    "column": location[key]["column"],
-                                    "message": warning["message"],
-                                    "option": warning["option"],
-                                }
-                            )
-                            # Found a caret, start, or end in location so
-                            # break out completely to address next warning
-                            break
-                    else:
-                        continue
-                    break
-
-        except json.JSONDecodeError:
-            continue  # Skip malformed JSON
-
-    return compiler_warnings
-
-
 def get_warnings_by_file(warnings: list[dict]) -> dict[str, list[dict]]:
     """
-    Returns a dictionary where the key is the file and the data is the warnings
-    in that file. Does not include duplicate warnings for a file from list of
-    provided warnings.
+    Returns a dictionary where the key is the file and the data is the
+    warnings in that file. Does not include duplicate warnings for a
+    file from list of provided warnings.
     """
     warnings_by_file = defaultdict(list)
     warnings_added = set()
@@ -124,22 +83,28 @@ def get_unexpected_warnings(
     are associated with a file that is not found in the list of files
     with expected warnings
     """
-    unexpected_warnings = []
+    unexpected_warnings = {}
     for file in files_with_warnings.keys():
         found_file_in_ignore_list = False
         for ignore_file in files_with_expected_warnings:
             if file == ignore_file.name:
                 if len(files_with_warnings[file]) > ignore_file.count:
-                    unexpected_warnings.extend(files_with_warnings[file])
+                    unexpected_warnings[file] = (files_with_warnings[file], ignore_file.count)
                 found_file_in_ignore_list = True
                 break
         if not found_file_in_ignore_list:
-            unexpected_warnings.extend(files_with_warnings[file])
+            unexpected_warnings[file] = (files_with_warnings[file], 0)
 
     if unexpected_warnings:
         print("Unexpected warnings:")
-        for warning in unexpected_warnings:
-            print(warning)
+        for file in unexpected_warnings:
+            print(
+                f"{file} expected {unexpected_warnings[file][1]} warnings,"
+                f" found {len(unexpected_warnings[file][0])}"
+            )
+            for warning in unexpected_warnings[file][0]:
+                print(warning)
+
         return 1
 
     return 0
@@ -156,14 +121,14 @@ def get_unexpected_improvements(
     unexpected_improvements = []
     for file in files_with_expected_warnings:
         if file.name not in files_with_warnings.keys():
-            unexpected_improvements.append(file)
+            unexpected_improvements.append((file.name, file.count, 0))
         elif len(files_with_warnings[file.name]) < file.count:
-                unexpected_improvements.append(file)
+            unexpected_improvements.append((file.name, file.count, len(files_with_warnings[file.name])))
 
     if unexpected_improvements:
         print("Unexpected improvements:")
         for file in unexpected_improvements:
-            print(file.name)
+            print(f"{file[0]} expected {file[1]} warnings, found {file[2]}")
         return 1
 
     return 0
@@ -204,8 +169,15 @@ def main(argv: list[str] | None = None) -> int:
         "--compiler-output-type",
         type=str,
         required=True,
-        choices=["json", "clang"],
-        help="Type of compiler output file (json or clang)",
+        choices=["gcc", "clang"],
+        help="Type of compiler output file (GCC or Clang)",
+    )
+    parser.add_argument(
+        "-p",
+        "--path-prefix",
+        type=str,
+        help="Path prefix to remove from the start of file paths"
+        " in compiler output",
     )
 
     args = parser.parse_args(argv)
@@ -241,7 +213,9 @@ def main(argv: list[str] | None = None) -> int:
             # where the first element is the file name and the second element
             # is the number of warnings expected in that file
             files_with_expected_warnings = {
-                FileWarnings(file.strip().split()[0], int(file.strip().split()[1]))
+                FileWarnings(
+                    file.strip().split()[0], int(file.strip().split()[1])
+                )
                 for file in clean_files
                 if file.strip() and not file.startswith("#")
             }
@@ -249,14 +223,11 @@ def main(argv: list[str] | None = None) -> int:
     with Path(args.compiler_output_file_path).open(encoding="UTF-8") as f:
         compiler_output_file_contents = f.read()
 
-    if args.compiler_output_type == "json":
-        warnings = extract_warnings_from_compiler_output_json(
-            compiler_output_file_contents
-        )
-    elif args.compiler_output_type == "clang":
-        warnings = extract_warnings_from_compiler_output_clang(
-            compiler_output_file_contents
-        )
+    warnings = extract_warnings_from_compiler_output(
+        compiler_output_file_contents,
+        args.compiler_output_type,
+        args.path_prefix
+    )
 
     files_with_warnings = get_warnings_by_file(warnings)
 
@@ -272,6 +243,11 @@ def main(argv: list[str] | None = None) -> int:
     if args.fail_on_improvement:
         exit_code |= status
 
+    print(
+        "For information about this tool and its configuration"
+        " visit https://devguide.python.org/development-tools/warnings/"
+        )
+
     return exit_code