[PATCH 4/9] scripts: python: Implement parsing of input data in convertPerfScriptProfile

[Anup Sharma]

The lines variable is created by splitting the profile string into individual
lines. It allows for iterating over each line for processing.

The line is considered the start of a sample. It is matched against a regular
expression pattern to extract relevant information such as before_time_stamp,
time_stamp, threadNamePidAndTidMatch, threadName, pid, and tid.

The stack frames of the current sample are then parsed in a nested loop.
Each stackFrameLine is matched against a regular expression pattern to
extract rawFunc and mod information.

Also fixed few checkpatch warnings.

Signed-off-by: Anup Sharma <anupnewsmail@xxxxxxxxx>
---
 .../scripts/python/firefox-gecko-converter.py | 62 ++++++++++++++++++-
 1 file changed, 60 insertions(+), 2 deletions(-)

diff --git a/tools/perf/scripts/python/firefox-gecko-converter.py b/tools/perf/scripts/python/firefox-gecko-converter.py
index 0ff70c0349c8..e5bc7a11c3e6 100644
--- a/tools/perf/scripts/python/firefox-gecko-converter.py
+++ b/tools/perf/scripts/python/firefox-gecko-converter.py
@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
 import re
 import sys
 import json
@@ -14,13 +15,13 @@ def isPerfScriptFormat(profile):
     firstLine = profile[:profile.index('\n')]
     return bool(re.match(r'^\S.*?\s+(?:\d+/)?\d+\s+(?:\d+\d+\s+)?[\d.]+:', firstLine))
 
-def convertPerfScriptProfile(profile): 
+def convertPerfScriptProfile(profile):
 
         def addSample(threadName, stackArray, time):
             nonlocal name
             if name != threadName:
                 name = threadName
-            # TODO: 
+            # TODO:
             # get_or_create_stack will create a new stack if it doesn't exist, or return the existing stack if it does.
             # get_or_create_frame will create a new frame if it doesn't exist, or return the existing frame if it does.
             stack = reduce(lambda prefix, stackFrame: get_or_create_stack(get_or_create_frame(stackFrame), prefix), stackArray, None)
@@ -54,3 +55,60 @@ def convertPerfScriptProfile(profile):
             thread = _createtread(threadName, pid, tid)
             threadMap[tid] = thread
         thread['addSample'](threadName, stack, time_stamp)
+
+    lines = profile.split('\n')
+
+    line_index = 0
+    startTime = 0
+    while line_index < len(lines):
+        line = lines[line_index]
+        line_index += 1
+    # perf script --header outputs header lines beginning with #
+        if line == '' or line.startswith('#'):
+            continue
+
+        sample_start_line = line
+
+        sample_start_match = re.match(r'^(.*)\s+([\d.]+):', sample_start_line)
+        if not sample_start_match:
+            print(f'Could not parse line as the start of a sample in the "perf script" profile format: "{sample_start_line}"')
+            continue
+
+        before_time_stamp = sample_start_match[1]
+        time_stamp = float(sample_start_match[2]) * 1000
+        threadNamePidAndTidMatch = re.match(r'^(.*)\s+(?:(\d+)\/)?(\d+)\b', before_time_stamp)
+
+        if not threadNamePidAndTidMatch:
+            print('Could not parse line as the start of a sample in the "perf script" profile format: "%s"' % sampleStartLine)
+            continue
+        threadName = threadNamePidAndTidMatch[1].strip()
+        pid = int(threadNamePidAndTidMatch[2] or 0)
+        tid = int(threadNamePidAndTidMatch[3] or 0)
+        if startTime == 0:
+            startTime = time_stamp
+        # Parse the stack frames of the current sample in a nested loop.
+        stack = []
+        while line_index < len(lines):
+            stackFrameLine = lines[line_index]
+            line_index += 1
+            if stackFrameLine.strip() == '':
+                # Sample ends.
+                break
+            stackFrameMatch = re.match(r'^\s*(\w+)\s*(.+) \(([^)]*)\)', stackFrameLine)
+            if stackFrameMatch:
+                rawFunc = stackFrameMatch[2]
+                mod = stackFrameMatch[3]
+                rawFunc = re.sub(r'\+0x[\da-f]+$', '', rawFunc)
+
+            if rawFunc.startswith('('):
+                continue # skip process names
+
+            if mod:
+                # If we have a module name, provide it.
+                # The code processing the profile will search for
+                # "functionName (in libraryName)" using a regexp,
+                # and automatically create the library information.
+                rawFunc += f' (in {mod})'
+
+            stack.append(rawFunc)
+
-- 
2.34.1