From b90b2953ea5b8d4387038aec46730afae13545d2 Mon Sep 17 00:00:00 2001
From: Christopher Haster <geky@geky.net>
Date: Wed, 4 Dec 2024 01:02:50 -0600
Subject: [PATCH] scripts: Some minor regex cleanup

Just trying to make regex in scripts a bit more consistent. Though regex
being regex this may be fruitless.
---
 scripts/code.py    |  8 ++++----
 scripts/ctx.py     |  8 ++++----
 scripts/data.py    |  8 ++++----
 scripts/perf.py    | 27 +++++++++++++--------------
 scripts/perfbd.py  | 27 +++++++++++++--------------
 scripts/structs.py |  8 ++++----
 6 files changed, 42 insertions(+), 44 deletions(-)

diff --git a/scripts/code.py b/scripts/code.py
index 7da027c2..9db4502f 100755
--- a/scripts/code.py
+++ b/scripts/code.py
@@ -420,12 +420,12 @@ def collect_dwarf_info(obj_path, tags=None, *,
         objdump_path=OBJDUMP_PATH,
         **args):
     info_pattern = re.compile(
-            '^\s*(?:<(?P<level>[^>]*)>'
+            '^\s*<(?P<level>[^>]*)>'
                     '\s*<(?P<off>[^>]*)>'
-                    '.*\(\s*(?P<tag>[^)]*?)\s*\)'
-                '|\s*<(?P<off_>[^>]*)>'
+                    '.*\(\s*(?P<tag>[^)]*?)\s*\)\s*$'
+                '|' '^\s*<(?P<off_>[^>]*)>'
                     '\s*(?P<at>[^>:]*?)'
-                    '\s*:(?P<v>.*))\s*$')
+                    '\s*:(?P<v>.*)\s*$')
 
     # collect dwarf entries
     info = co.OrderedDict()
diff --git a/scripts/ctx.py b/scripts/ctx.py
index 017d8d24..8a644b3d 100755
--- a/scripts/ctx.py
+++ b/scripts/ctx.py
@@ -429,12 +429,12 @@ def collect_dwarf_info(obj_path, tags=None, *,
         objdump_path=OBJDUMP_PATH,
         **args):
     info_pattern = re.compile(
-            '^\s*(?:<(?P<level>[^>]*)>'
+            '^\s*<(?P<level>[^>]*)>'
                     '\s*<(?P<off>[^>]*)>'
-                    '.*\(\s*(?P<tag>[^)]*?)\s*\)'
-                '|\s*<(?P<off_>[^>]*)>'
+                    '.*\(\s*(?P<tag>[^)]*?)\s*\)\s*$'
+                '|' '^\s*<(?P<off_>[^>]*)>'
                     '\s*(?P<at>[^>:]*?)'
-                    '\s*:(?P<v>.*))\s*$')
+                    '\s*:(?P<v>.*)\s*$')
 
     # collect dwarf entries
     info = co.OrderedDict()
diff --git a/scripts/data.py b/scripts/data.py
index e8c09347..63c636fc 100755
--- a/scripts/data.py
+++ b/scripts/data.py
@@ -420,12 +420,12 @@ def collect_dwarf_info(obj_path, tags=None, *,
         objdump_path=OBJDUMP_PATH,
         **args):
     info_pattern = re.compile(
-            '^\s*(?:<(?P<level>[^>]*)>'
+            '^\s*<(?P<level>[^>]*)>'
                     '\s*<(?P<off>[^>]*)>'
-                    '.*\(\s*(?P<tag>[^)]*?)\s*\)'
-                '|\s*<(?P<off_>[^>]*)>'
+                    '.*\(\s*(?P<tag>[^)]*?)\s*\)\s*$'
+                '|' '^\s*<(?P<off_>[^>]*)>'
                     '\s*(?P<at>[^>:]*?)'
-                    '\s*:(?P<v>.*))\s*$')
+                    '\s*:(?P<v>.*)\s*$')
 
     # collect dwarf entries
     info = co.OrderedDict()
diff --git a/scripts/perf.py b/scripts/perf.py
index 3edd1b86..4674768d 100755
--- a/scripts/perf.py
+++ b/scripts/perf.py
@@ -447,22 +447,21 @@ def collect_dwarf_lines(obj_path, *,
         objdump_path=OBJDUMP_PATH,
         **args):
     line_pattern = re.compile(
-            '^\s*(?:'
-                # matches dir/file table
-                '(?P<no>[0-9]+)'
+            # matches dir/file table
+            '^\s*(?P<no>[0-9]+)'
                     '(?:\s+(?P<dir>[0-9]+))?'
-                    '.*\s+(?P<path>[^\s]+)'
+                    '.*\s+(?P<path>[^\s]+)\s*$'
                 # matches line opcodes
-                '|' '\[[^\]]*\]\s+' '(?:'
-                    '(?P<op_special>Special)'
-                    '|' '(?P<op_copy>Copy)'
-                    '|' '(?P<op_end>End of Sequence)'
-                    '|' 'File .*?to (?:entry )?(?P<op_file>\d+)'
-                    '|' 'Line .*?to (?P<op_line>[0-9]+)'
-                    '|' '(?:Address|PC) .*?to (?P<op_addr>[0x0-9a-fA-F]+)'
-                    '|' '.'
-                ')*'
-            ')\s*$', re.IGNORECASE)
+                '|' '^\s*\[[^\]]*\]' '(?:'
+                    '\s+(?P<op_special>Special)'
+                        '|' '\s+(?P<op_copy>Copy)'
+                        '|' '\s+(?P<op_end>End of Sequence)'
+                        '|' '\s+File.*?to.*?(?P<op_file>[0-9]+)'
+                        '|' '\s+Line.*?to.*?(?P<op_line>[0-9]+)'
+                        '|' '\s+(?:Address|PC)'
+                            '\s+.*?to.*?(?P<op_addr>[0xX0-9a-fA-F]+)'
+                        '|' '\s+[^\s]+' ')+\s*$',
+            re.IGNORECASE)
 
     # state machine for dwarf line numbers, note that objdump's
     # decodedline seems to have issues with multiple dir/file
diff --git a/scripts/perfbd.py b/scripts/perfbd.py
index 61f8bf52..51682194 100755
--- a/scripts/perfbd.py
+++ b/scripts/perfbd.py
@@ -352,22 +352,21 @@ def collect_dwarf_lines(obj_path, *,
         objdump_path=OBJDUMP_PATH,
         **args):
     line_pattern = re.compile(
-            '^\s*(?:'
-                # matches dir/file table
-                '(?P<no>[0-9]+)'
+            # matches dir/file table
+            '^\s*(?P<no>[0-9]+)'
                     '(?:\s+(?P<dir>[0-9]+))?'
-                    '.*\s+(?P<path>[^\s]+)'
+                    '.*\s+(?P<path>[^\s]+)\s*$'
                 # matches line opcodes
-                '|' '\[[^\]]*\]\s+' '(?:'
-                    '(?P<op_special>Special)'
-                    '|' '(?P<op_copy>Copy)'
-                    '|' '(?P<op_end>End of Sequence)'
-                    '|' 'File .*?to (?:entry )?(?P<op_file>\d+)'
-                    '|' 'Line .*?to (?P<op_line>[0-9]+)'
-                    '|' '(?:Address|PC) .*?to (?P<op_addr>[0x0-9a-fA-F]+)'
-                    '|' '.'
-                ')*'
-            ')\s*$', re.IGNORECASE)
+                '|' '^\s*\[[^\]]*\]' '(?:'
+                    '\s+(?P<op_special>Special)'
+                        '|' '\s+(?P<op_copy>Copy)'
+                        '|' '\s+(?P<op_end>End of Sequence)'
+                        '|' '\s+File.*?to.*?(?P<op_file>[0-9]+)'
+                        '|' '\s+Line.*?to.*?(?P<op_line>[0-9]+)'
+                        '|' '\s+(?:Address|PC)'
+                            '\s+.*?to.*?(?P<op_addr>[0xX0-9a-fA-F]+)'
+                        '|' '\s+[^\s]+' ')+\s*$',
+            re.IGNORECASE)
 
     # state machine for dwarf line numbers, note that objdump's
     # decodedline seems to have issues with multiple dir/file
diff --git a/scripts/structs.py b/scripts/structs.py
index 353dbc16..3f9ddba4 100755
--- a/scripts/structs.py
+++ b/scripts/structs.py
@@ -317,12 +317,12 @@ def collect_dwarf_info(obj_path, tags=None, *,
         objdump_path=OBJDUMP_PATH,
         **args):
     info_pattern = re.compile(
-            '^\s*(?:<(?P<level>[^>]*)>'
+            '^\s*<(?P<level>[^>]*)>'
                     '\s*<(?P<off>[^>]*)>'
-                    '.*\(\s*(?P<tag>[^)]*?)\s*\)'
-                '|\s*<(?P<off_>[^>]*)>'
+                    '.*\(\s*(?P<tag>[^)]*?)\s*\)\s*$'
+                '|' '^\s*<(?P<off_>[^>]*)>'
                     '\s*(?P<at>[^>:]*?)'
-                    '\s*:(?P<v>.*))\s*$')
+                    '\s*:(?P<v>.*)\s*$')
 
     # collect dwarf entries
     info = co.OrderedDict()