[Lldb-commits] [lldb] 28d0c0c - [lldb] Tidy some regex in crashlog.py (NFC)
Dave Lee via lldb-commits
lldb-commits at lists.llvm.org
Thu Aug 11 15:25:13 PDT 2022
Author: Dave Lee
Date: 2022-08-11T15:24:57-07:00
New Revision: 28d0c0c2c8e88d2b6599ee34c84eb58eed43a626
URL: https://github.com/llvm/llvm-project/commit/28d0c0c2c8e88d2b6599ee34c84eb58eed43a626
DIFF: https://github.com/llvm/llvm-project/commit/28d0c0c2c8e88d2b6599ee34c84eb58eed43a626.diff
LOG: [lldb] Tidy some regex in crashlog.py (NFC)
A spiritual follow up to D131032. I noticed some regex could be simplified.
This does some of the following:
1. Removes unused capture groups
2. Uses non-capturing `(?:...)` groups where grouping is needed but capturing isn't
3. Removes trailing `.*`
4. Uses `\d` over `[0-9]`
5. Uses raw strings
6. Uses `{N,}` to indicate N-or-more
Also improves the call site of a `re.findall`.
Differential Revision: https://reviews.llvm.org/D131305
Added:
Modified:
lldb/examples/python/crashlog.py
lldb/test/Shell/ScriptInterpreter/Python/Crashlog/parser_text.test
Removed:
################################################################################
diff --git a/lldb/examples/python/crashlog.py b/lldb/examples/python/crashlog.py
index 33f4c4f3b3680..ad0d70a669a85 100755
--- a/lldb/examples/python/crashlog.py
+++ b/lldb/examples/python/crashlog.py
@@ -603,26 +603,26 @@ class CrashLogParseMode:
class TextCrashLogParser(CrashLogParser):
- parent_process_regex = re.compile('^Parent Process:\s*(.*)\[(\d+)\]')
- thread_state_regex = re.compile('^Thread ([0-9]+) crashed with')
- thread_instrs_regex = re.compile('^Thread ([0-9]+) instruction stream')
- thread_regex = re.compile('^Thread ([0-9]+)([^:]*):(.*)')
- app_backtrace_regex = re.compile('^Application Specific Backtrace ([0-9]+)([^:]*):(.*)')
- version = r'(\(.+\)|(arm|x86_)[0-9a-z]+)\s+'
- frame_regex = re.compile(r'^([0-9]+)' r'\s+' # id
- r'(.+?)' r'\s+' # img_name
- r'(' +version+ r')?' # img_version
- r'(0x[0-9a-fA-F]{7,})' # addr (7 chars or more)
- r' +(.*)' # offs
+ parent_process_regex = re.compile(r'^Parent Process:\s*(.*)\[(\d+)\]')
+ thread_state_regex = re.compile(r'^Thread \d+ crashed with')
+ thread_instrs_regex = re.compile(r'^Thread \d+ instruction stream')
+ thread_regex = re.compile(r'^Thread (\d+).*:')
+ app_backtrace_regex = re.compile(r'^Application Specific Backtrace (\d+).*:')
+ version = r'\(.+\)|(?:arm|x86_)[0-9a-z]+'
+ frame_regex = re.compile(r'^(\d+)\s+' # id
+ r'(.+?)\s+' # img_name
+ r'(?:' +version+ r'\s+)?' # img_version
+ r'(0x[0-9a-fA-F]{7,})' # addr (7 chars or more)
+ r' +(.*)' # offs
)
- null_frame_regex = re.compile(r'^([0-9]+)\s+\?\?\?\s+(0{7}0+) +(.*)')
- image_regex_uuid = re.compile(r'(0x[0-9a-fA-F]+)' # img_lo
- r'\s+' '-' r'\s+' # -
- r'(0x[0-9a-fA-F]+)' r'\s+' # img_hi
- r'[+]?(.+?)' r'\s+' # img_name
- r'(' +version+ ')?' # img_version
- r'(<([-0-9a-fA-F]+)>\s+)?' # img_uuid
- r'(/.*)' # img_path
+ null_frame_regex = re.compile(r'^\d+\s+\?\?\?\s+0{7,} +')
+ image_regex_uuid = re.compile(r'(0x[0-9a-fA-F]+)' # img_lo
+ r'\s+-\s+' # -
+ r'(0x[0-9a-fA-F]+)\s+' # img_hi
+ r'[+]?(.+?)\s+' # img_name
+ r'(?:(' +version+ r')\s+)?' # img_version
+ r'(?:<([-0-9a-fA-F]+)>\s+)?' # img_uuid
+ r'(/.*)' # img_path
)
def __init__(self, debugger, path, verbose):
@@ -768,8 +768,8 @@ def parse_thread(self, line):
return
frame_match = self.frame_regex.search(line)
if frame_match:
- (frame_id, frame_img_name, _, frame_img_version, _,
- frame_addr, frame_ofs) = frame_match.groups()
+ (frame_id, frame_img_name, frame_addr,
+ frame_ofs) = frame_match.groups()
ident = frame_img_name
self.thread.add_ident(ident)
if ident not in self.crashlog.idents:
@@ -782,8 +782,8 @@ def parse_thread(self, line):
def parse_images(self, line):
image_match = self.image_regex_uuid.search(line)
if image_match:
- (img_lo, img_hi, img_name, _, img_version, _,
- _, img_uuid, img_path) = image_match.groups()
+ (img_lo, img_hi, img_name, img_version,
+ img_uuid, img_path) = image_match.groups()
image = self.crashlog.DarwinImage(int(img_lo, 0), int(img_hi, 0),
img_name.strip(),
img_version.strip()
@@ -796,13 +796,10 @@ def parse_images(self, line):
def parse_thread_registers(self, line):
- stripped_line = line.strip()
# "r12: 0x00007fff6b5939c8 r13: 0x0000000007000006 r14: 0x0000000000002a03 r15: 0x0000000000000c00"
- reg_values = re.findall(
- '([a-zA-Z0-9]+: 0[Xx][0-9a-fA-F]+) *', stripped_line)
- for reg_value in reg_values:
- (reg, value) = reg_value.split(': ')
- self.thread.registers[reg.strip()] = int(value, 0)
+ reg_values = re.findall('([a-z0-9]+): (0x[0-9a-f]+)', line, re.I)
+ for reg, value in reg_values:
+ self.thread.registers[reg] = int(value, 16)
def parse_system(self, line):
self.crashlog.system_profile.append(line)
diff --git a/lldb/test/Shell/ScriptInterpreter/Python/Crashlog/parser_text.test b/lldb/test/Shell/ScriptInterpreter/Python/Crashlog/parser_text.test
index 7251d8541be10..af3f9ad48662b 100644
--- a/lldb/test/Shell/ScriptInterpreter/Python/Crashlog/parser_text.test
+++ b/lldb/test/Shell/ScriptInterpreter/Python/Crashlog/parser_text.test
@@ -52,7 +52,6 @@ images = [
# CHECK: MyFramework Plus.dylib
# CHECK: ({{.*}}
# CHECK: 1.11 - MyFramework 1.11
-# CHECK: <{{.*}}
# CHECK: 01234
# CHECK: /tmp/MyFramework Plus.dylib
@@ -62,7 +61,6 @@ images = [
# CHECK: MyFramework-dev.dylib
# CHECK: ({{.*}}
# CHECK: 1.0.0svn - 1.0.0svn
-# CHECK: <{{.*}}
# CHECK: 01234
# CHECK: /MyFramework-dev.dylib
@@ -73,7 +71,6 @@ images = [
# CHECK: ({{.*}}
# CHECK: 400.9.4
# CHECK: None
-# CHECK: None
# CHECK: /usr/lib/libc++.1.dylib
"0x1047b8000 - 0x10481ffff dyld arm64e <cfa789d10da63f9a8996daf84ed9d04f> /usr/lib/dyld"
@@ -82,7 +79,6 @@ images = [
# CHECK: dyld
# CHECK: {{.*}}
# CHECK: arm64e
-# CHECK: <{{.*}}
# CHECK: cfa789d10da63f9a8996daf84ed9d04f
# CHECK: /usr/lib/dyld
]
@@ -101,9 +97,6 @@ frames = [
"2 MyApp Pro arm64 0x000000019b0db3a8 foo + 72",
# CHECK: 2
# CHECK: MyApp Pro
-# CHECK: a
-# CHECK: arm64
-# CHECK: a
# CHECK: 0x000000019b0db3a8
# CHECK: foo + 72
"3 He 0x1 0x000000019b0db3a8 foo + 72"
More information about the lldb-commits
mailing list