From 7526b469b95a6ff519be893578937f871fbd8fc5 Mon Sep 17 00:00:00 2001
From: Christopher Haster <geky@geky.net>
Date: Thu, 15 May 2025 14:28:52 -0500
Subject: [PATCH] scripts: Adopted globs in all field matchers (-D/--define,
 -c/--compare)

Globs in CLI attrs (-L'*=bs=%(bs)s' for example), have been remarkably
useful. It makes sense to extend this to the other flags that match
against CSV fields, though this does add complexity to a large number of
smaller scripts.

- -D/--define can now use globs when filtering:

    $ ./scripts/code.py lfs.o -Dfunction='lfsr_file_*'

  -D/--define already accepted a comma-separated list of options, so
  extending this to globs makes sense.

  Note this differs from test.py/bench.py's -D/--define. Globbing in
  test.py/bench.py wouldn't really work since -D/--define is generative,
  not matching. But there's already other differences such as integer
  parsing, range, etc. It's not worth making these perfectly consistent
  as they are really two different tools that just happen to look the
  same.

- -c/--compare now matches with globs when finding the compare entry:

    $ ./scripts/code.py lfs.o -c'lfs*_file_sync'

  This is quite a bit less useful that -D/--define, but makes sense for
  consistency.

  Note -c/--compare just chooses the first match. It doesn't really make
  sense to compare against multiple entries.

This raised the question of globs in the field specifiers themselves
(-f'bench_*' for example), but I'm rejecting this for now as I need to
draw the complexity/scope _somewhere_, and I'm worried it's already way
over on the too-complex side.

So, for now, field names must always be specified explicitly. Globbing
field names would add too much complexity. Especially considering how
many flags accept field names in these scripts.
---
 scripts/code.py      | 16 +++++++++++++---
 scripts/cov.py       | 16 +++++++++++++---
 scripts/csv.py       | 19 +++++++++++++++----
 scripts/ctx.py       | 16 +++++++++++++---
 scripts/data.py      | 16 +++++++++++++---
 scripts/perf.py      | 16 +++++++++++++---
 scripts/perfbd.py    | 16 +++++++++++++---
 scripts/plot.py      | 10 +++++++---
 scripts/plotmpl.py   | 10 +++++++---
 scripts/stack.py     | 16 +++++++++++++---
 scripts/structs.py   | 20 +++++++++++++++-----
 scripts/treemap.py   | 11 ++++++++---
 scripts/treemapd3.py | 11 ++++++++---
 13 files changed, 151 insertions(+), 42 deletions(-)

diff --git a/scripts/code.py b/scripts/code.py
index 8c071b69..1caf27b7 100755
--- a/scripts/code.py
+++ b/scripts/code.py
@@ -18,6 +18,7 @@ if __name__ == "__main__":
 
 import collections as co
 import csv
+import fnmatch
 import functools as ft
 import io
 import itertools as it
@@ -543,7 +544,9 @@ def fold(Result, results, *,
     if defines:
         results_ = []
         for r in results:
-            if all(str(getattr(r, k)) in vs for k, vs in defines):
+            if all(any(fnmatch.fnmatchcase(str(getattr(r, k, '')), v)
+                        for v in vs)
+                    for k, vs in defines):
                 results_.append(r)
         results = results_
 
@@ -634,7 +637,13 @@ def table(Result, results, diff_results=None, *,
 
     # find compare entry if there is one
     if compare:
-        compare_r = table.get(','.join(str(k) for k in compare))
+        compare_ = min(
+            (n for n in table.keys()
+                if all(fnmatch.fnmatchcase(k, c)
+                    for k, c in it.zip_longest(n.split(','), compare,
+                        fillvalue=''))),
+            default=compare)
+        compare_r = table.get(compare_)
 
     # build up our lines
     lines = []
@@ -1156,7 +1165,8 @@ if __name__ == "__main__":
                     k.strip(),
                     {v.strip() for v in vs.split(',')})
                 )(*x.split('=', 1)),
-            help="Only include results where this field is this value.")
+            help="Only include results where this field is this value. May "
+                "include comma-separated options and globs.")
     class AppendSort(argparse.Action):
         def __call__(self, parser, namespace, value, option):
             if namespace.sort is None:
diff --git a/scripts/cov.py b/scripts/cov.py
index 9bc35c84..a85582c5 100755
--- a/scripts/cov.py
+++ b/scripts/cov.py
@@ -18,6 +18,7 @@ if __name__ == "__main__":
 
 import collections as co
 import csv
+import fnmatch
 import io
 import itertools as it
 import json
@@ -403,7 +404,9 @@ def fold(Result, results, *,
     if defines:
         results_ = []
         for r in results:
-            if all(str(getattr(r, k)) in vs for k, vs in defines):
+            if all(any(fnmatch.fnmatchcase(str(getattr(r, k, '')), v)
+                        for v in vs)
+                    for k, vs in defines):
                 results_.append(r)
         results = results_
 
@@ -494,7 +497,13 @@ def table(Result, results, diff_results=None, *,
 
     # find compare entry if there is one
     if compare:
-        compare_r = table.get(','.join(str(k) for k in compare))
+        compare_ = min(
+            (n for n in table.keys()
+                if all(fnmatch.fnmatchcase(k, c)
+                    for k, c in it.zip_longest(n.split(','), compare,
+                        fillvalue=''))),
+            default=compare)
+        compare_r = table.get(compare_)
 
     # build up our lines
     lines = []
@@ -1126,7 +1135,8 @@ if __name__ == "__main__":
                     k.strip(),
                     {v.strip() for v in vs.split(',')})
                 )(*x.split('=', 1)),
-            help="Only include results where this field is this value.")
+            help="Only include results where this field is this value. May "
+                "include comma-separated options and globs.")
     class AppendSort(argparse.Action):
         def __call__(self, parser, namespace, value, option):
             if namespace.sort is None:
diff --git a/scripts/csv.py b/scripts/csv.py
index dee8f2aa..f96ae1ca 100755
--- a/scripts/csv.py
+++ b/scripts/csv.py
@@ -16,6 +16,7 @@ if __name__ == "__main__":
 
 import collections as co
 import csv
+import fnmatch
 import functools as ft
 import itertools as it
 import math as mt
@@ -1566,7 +1567,9 @@ def homogenize(Result, results, *,
         # evaluation order of exprs/mods/etc, note this isn't really
         # inconsistent with the other scripts, since they don't really
         # evaluate anything
-        if not all(k in r and str(r[k]) in vs for k, vs in defines):
+        if not all(any(fnmatch.fnmatchcase(str(r.get(k, '')), v)
+                    for v in vs)
+                for k, vs in defines):
             continue
 
         # append a result
@@ -1628,7 +1631,9 @@ def fold(Result, results, *,
     if defines:
         results_ = []
         for r in results:
-            if all(str(getattr(r, k)) in vs for k, vs in defines):
+            if all(any(fnmatch.fnmatchcase(str(getattr(r, k, '')), v)
+                        for v in vs)
+                    for k, vs in defines):
                 results_.append(r)
         results = results_
 
@@ -1766,7 +1771,13 @@ def table(Result, results, diff_results=None, *,
 
     # find compare entry if there is one
     if compare:
-        compare_r = table.get(','.join(str(k) for k in compare))
+        compare_ = min(
+            (n for n in table.keys()
+                if all(fnmatch.fnmatchcase(k, c)
+                    for k, c in it.zip_longest(n.split(','), compare,
+                        fillvalue=''))),
+            default=compare)
+        compare_r = table.get(compare_)
 
     # build up our lines
     lines = []
@@ -2496,7 +2507,7 @@ if __name__ == "__main__":
                     {v.strip() for v in vs.split(',')})
                 )(*x.split('=', 1)),
             help="Only include results where this field is this value. May "
-                "include comma-separated options.")
+                "include comma-separated options and globs.")
     class AppendSort(argparse.Action):
         def __call__(self, parser, namespace, value, option):
             if namespace.sort is None:
diff --git a/scripts/ctx.py b/scripts/ctx.py
index 0f3f3318..7e0acad0 100755
--- a/scripts/ctx.py
+++ b/scripts/ctx.py
@@ -15,6 +15,7 @@ if __name__ == "__main__":
 
 import collections as co
 import csv
+import fnmatch
 import functools as ft
 import io
 import itertools as it
@@ -756,7 +757,9 @@ def fold(Result, results, *,
     if defines:
         results_ = []
         for r in results:
-            if all(str(getattr(r, k)) in vs for k, vs in defines):
+            if all(any(fnmatch.fnmatchcase(str(getattr(r, k, '')), v)
+                        for v in vs)
+                    for k, vs in defines):
                 results_.append(r)
         results = results_
 
@@ -894,7 +897,13 @@ def table(Result, results, diff_results=None, *,
 
     # find compare entry if there is one
     if compare:
-        compare_r = table.get(','.join(str(k) for k in compare))
+        compare_ = min(
+            (n for n in table.keys()
+                if all(fnmatch.fnmatchcase(k, c)
+                    for k, c in it.zip_longest(n.split(','), compare,
+                        fillvalue=''))),
+            default=compare)
+        compare_r = table.get(compare_)
 
     # build up our lines
     lines = []
@@ -1452,7 +1461,8 @@ if __name__ == "__main__":
                     k.strip(),
                     {v.strip() for v in vs.split(',')})
                 )(*x.split('=', 1)),
-            help="Only include results where this field is this value.")
+            help="Only include results where this field is this value. May "
+                "include comma-separated options and globs.")
     class AppendSort(argparse.Action):
         def __call__(self, parser, namespace, value, option):
             if namespace.sort is None:
diff --git a/scripts/data.py b/scripts/data.py
index 3c9a9316..91594bd9 100755
--- a/scripts/data.py
+++ b/scripts/data.py
@@ -18,6 +18,7 @@ if __name__ == "__main__":
 
 import collections as co
 import csv
+import fnmatch
 import functools as ft
 import io
 import itertools as it
@@ -543,7 +544,9 @@ def fold(Result, results, *,
     if defines:
         results_ = []
         for r in results:
-            if all(str(getattr(r, k)) in vs for k, vs in defines):
+            if all(any(fnmatch.fnmatchcase(str(getattr(r, k, '')), v)
+                        for v in vs)
+                    for k, vs in defines):
                 results_.append(r)
         results = results_
 
@@ -634,7 +637,13 @@ def table(Result, results, diff_results=None, *,
 
     # find compare entry if there is one
     if compare:
-        compare_r = table.get(','.join(str(k) for k in compare))
+        compare_ = min(
+            (n for n in table.keys()
+                if all(fnmatch.fnmatchcase(k, c)
+                    for k, c in it.zip_longest(n.split(','), compare,
+                        fillvalue=''))),
+            default=compare)
+        compare_r = table.get(compare_)
 
     # build up our lines
     lines = []
@@ -1156,7 +1165,8 @@ if __name__ == "__main__":
                     k.strip(),
                     {v.strip() for v in vs.split(',')})
                 )(*x.split('=', 1)),
-            help="Only include results where this field is this value.")
+            help="Only include results where this field is this value. May "
+                "include comma-separated options and globs.")
     class AppendSort(argparse.Action):
         def __call__(self, parser, namespace, value, option):
             if namespace.sort is None:
diff --git a/scripts/perf.py b/scripts/perf.py
index 51b14316..c99dd1f4 100755
--- a/scripts/perf.py
+++ b/scripts/perf.py
@@ -19,6 +19,7 @@ import collections as co
 import csv
 import errno
 import fcntl
+import fnmatch
 import functools as ft
 import io
 import itertools as it
@@ -857,7 +858,9 @@ def fold(Result, results, *,
     if defines:
         results_ = []
         for r in results:
-            if all(str(getattr(r, k)) in vs for k, vs in defines):
+            if all(any(fnmatch.fnmatchcase(str(getattr(r, k, '')), v)
+                        for v in vs)
+                    for k, vs in defines):
                 results_.append(r)
         results = results_
 
@@ -995,7 +998,13 @@ def table(Result, results, diff_results=None, *,
 
     # find compare entry if there is one
     if compare:
-        compare_r = table.get(','.join(str(k) for k in compare))
+        compare_ = min(
+            (n for n in table.keys()
+                if all(fnmatch.fnmatchcase(k, c)
+                    for k, c in it.zip_longest(n.split(','), compare,
+                        fillvalue=''))),
+            default=compare)
+        compare_r = table.get(compare_)
 
     # build up our lines
     lines = []
@@ -1698,7 +1707,8 @@ if __name__ == "__main__":
                     k.strip(),
                     {v.strip() for v in vs.split(',')})
                 )(*x.split('=', 1)),
-            help="Only include results where this field is this value.")
+            help="Only include results where this field is this value. May "
+                "include comma-separated options and globs.")
     class AppendSort(argparse.Action):
         def __call__(self, parser, namespace, value, option):
             if namespace.sort is None:
diff --git a/scripts/perfbd.py b/scripts/perfbd.py
index 745934b5..d496710d 100755
--- a/scripts/perfbd.py
+++ b/scripts/perfbd.py
@@ -18,6 +18,7 @@ if __name__ == "__main__":
 import bisect
 import collections as co
 import csv
+import fnmatch
 import functools as ft
 import io
 import itertools as it
@@ -831,7 +832,9 @@ def fold(Result, results, *,
     if defines:
         results_ = []
         for r in results:
-            if all(str(getattr(r, k)) in vs for k, vs in defines):
+            if all(any(fnmatch.fnmatchcase(str(getattr(r, k, '')), v)
+                        for v in vs)
+                    for k, vs in defines):
                 results_.append(r)
         results = results_
 
@@ -969,7 +972,13 @@ def table(Result, results, diff_results=None, *,
 
     # find compare entry if there is one
     if compare:
-        compare_r = table.get(','.join(str(k) for k in compare))
+        compare_ = min(
+            (n for n in table.keys()
+                if all(fnmatch.fnmatchcase(k, c)
+                    for k, c in it.zip_longest(n.split(','), compare,
+                        fillvalue=''))),
+            default=compare)
+        compare_r = table.get(compare_)
 
     # build up our lines
     lines = []
@@ -1699,7 +1708,8 @@ if __name__ == "__main__":
                     k.strip(),
                     {v.strip() for v in vs.split(',')})
                 )(*x.split('=', 1)),
-            help="Only include results where this field is this value.")
+            help="Only include results where this field is this value. May "
+                "include comma-separated options and globs.")
     class AppendSort(argparse.Action):
         def __call__(self, parser, namespace, value, option):
             if namespace.sort is None:
diff --git a/scripts/plot.py b/scripts/plot.py
index 7a9a0e26..4dc5eba0 100755
--- a/scripts/plot.py
+++ b/scripts/plot.py
@@ -327,7 +327,9 @@ def collect(csv_paths, defines=[]):
                             if k not in fields)
                 for r in reader:
                     # filter by matching defines
-                    if not all(k in r and r[k] in vs for k, vs in defines):
+                    if not all(any(fnmatch.fnmatchcase(r.get(k, ''), v)
+                                for v in vs)
+                            for k, vs in defines):
                         continue
 
                     results.append(r)
@@ -341,7 +343,9 @@ def fold(results, by=None, x=None, y=None, defines=[]):
     if defines:
         results_ = []
         for r in results:
-            if all(k in r and r[k] in vs for k, vs in defines):
+            if all(any(fnmatch.fnmatchcase(r.get(k, ''), v)
+                        for v in vs)
+                    for k, vs in defines):
                 results_.append(r)
         results = results_
 
@@ -1913,7 +1917,7 @@ if __name__ == "__main__":
                 )(*x.split('=', 1)),
             action='append',
             help="Only include results where this field is this value. May "
-                "include comma-separated options.")
+                "include comma-separated options and globs.")
     parser.add_argument(
             '-L', '--add-label',
             dest='labels',
diff --git a/scripts/plotmpl.py b/scripts/plotmpl.py
index edd5bf68..fa3adf6f 100755
--- a/scripts/plotmpl.py
+++ b/scripts/plotmpl.py
@@ -211,7 +211,9 @@ def collect(csv_paths, defines=[]):
                             if k not in fields)
                 for r in reader:
                     # filter by matching defines
-                    if not all(k in r and r[k] in vs for k, vs in defines):
+                    if not all(any(fnmatch.fnmatchcase(r.get(k, ''), v)
+                                for v in vs)
+                            for k, vs in defines):
                         continue
 
                     results.append(r)
@@ -225,7 +227,9 @@ def fold(results, by=None, x=None, y=None, defines=[]):
     if defines:
         results_ = []
         for r in results:
-            if all(k in r and r[k] in vs for k, vs in defines):
+            if all(any(fnmatch.fnmatchcase(r.get(k, ''), v)
+                        for v in vs)
+                    for k, vs in defines):
                 results_.append(r)
         results = results_
 
@@ -1367,7 +1371,7 @@ if __name__ == "__main__":
                 )(*x.split('=', 1)),
             action='append',
             help="Only include results where this field is this value. May "
-                "include comma-separated options.")
+                "include comma-separated options and globs.")
     parser.add_argument(
             '-L', '--add-label',
             dest='labels',
diff --git a/scripts/stack.py b/scripts/stack.py
index 42615423..38329e37 100755
--- a/scripts/stack.py
+++ b/scripts/stack.py
@@ -16,6 +16,7 @@ if __name__ == "__main__":
 
 import collections as co
 import csv
+import fnmatch
 import functools as ft
 import io
 import itertools as it
@@ -499,7 +500,9 @@ def fold(Result, results, *,
     if defines:
         results_ = []
         for r in results:
-            if all(str(getattr(r, k)) in vs for k, vs in defines):
+            if all(any(fnmatch.fnmatchcase(str(getattr(r, k, '')), v)
+                        for v in vs)
+                    for k, vs in defines):
                 results_.append(r)
         results = results_
 
@@ -637,7 +640,13 @@ def table(Result, results, diff_results=None, *,
 
     # find compare entry if there is one
     if compare:
-        compare_r = table.get(','.join(str(k) for k in compare))
+        compare_ = min(
+            (n for n in table.keys()
+                if all(fnmatch.fnmatchcase(k, c)
+                    for k, c in it.zip_longest(n.split(','), compare,
+                        fillvalue=''))),
+            default=compare)
+        compare_r = table.get(compare_)
 
     # build up our lines
     lines = []
@@ -1197,7 +1206,8 @@ if __name__ == "__main__":
                     k.strip(),
                     {v.strip() for v in vs.split(',')})
                 )(*x.split('=', 1)),
-            help="Only include results where this field is this value.")
+            help="Only include results where this field is this value. May "
+                "include comma-separated options and globs.")
     class AppendSort(argparse.Action):
         def __call__(self, parser, namespace, value, option):
             if namespace.sort is None:
diff --git a/scripts/structs.py b/scripts/structs.py
index 926a1092..56a16d6f 100755
--- a/scripts/structs.py
+++ b/scripts/structs.py
@@ -15,9 +15,10 @@ if __name__ == "__main__":
 
 import collections as co
 import csv
-import itertools as it
-import io
+import fnmatch
 import functools as ft
+import io
+import itertools as it
 import math as mt
 import os
 import re
@@ -637,7 +638,9 @@ def fold(Result, results, *,
     if defines:
         results_ = []
         for r in results:
-            if all(str(getattr(r, k)) in vs for k, vs in defines):
+            if all(any(fnmatch.fnmatchcase(str(getattr(r, k, '')), v)
+                        for v in vs)
+                    for k, vs in defines):
                 results_.append(r)
         results = results_
 
@@ -775,7 +778,13 @@ def table(Result, results, diff_results=None, *,
 
     # find compare entry if there is one
     if compare:
-        compare_r = table.get(','.join(str(k) for k in compare))
+        compare_ = min(
+            (n for n in table.keys()
+                if all(fnmatch.fnmatchcase(k, c)
+                    for k, c in it.zip_longest(n.split(','), compare,
+                        fillvalue=''))),
+            default=compare)
+        compare_r = table.get(compare_)
 
     # build up our lines
     lines = []
@@ -1333,7 +1342,8 @@ if __name__ == "__main__":
                     k.strip(),
                     {v.strip() for v in vs.split(',')})
                 )(*x.split('=', 1)),
-            help="Only include results where this field is this value.")
+            help="Only include results where this field is this value. May "
+                "include comma-separated options and globs.")
     class AppendSort(argparse.Action):
         def __call__(self, parser, namespace, value, option):
             if namespace.sort is None:
diff --git a/scripts/treemap.py b/scripts/treemap.py
index 226b145c..e49ef688 100755
--- a/scripts/treemap.py
+++ b/scripts/treemap.py
@@ -236,7 +236,9 @@ def collect(csv_paths, defines=[]):
                             if k not in fields)
                 for r in reader:
                     # filter by matching defines
-                    if not all(k in r and r[k] in vs for k, vs in defines):
+                    if not all(any(fnmatch.fnmatchcase(r.get(k, ''), v)
+                                for v in vs)
+                            for k, vs in defines):
                         continue
 
                     results.append(r)
@@ -250,7 +252,9 @@ def fold(results, by=None, fields=None, defines=[]):
     if defines:
         results_ = []
         for r in results:
-            if all(k in r and r[k] in vs for k, vs in defines):
+            if all(any(fnmatch.fnmatchcase(r.get(k, ''), v)
+                        for v in vs)
+                    for k, vs in defines):
                 results_.append(r)
         results = results_
 
@@ -1339,7 +1343,8 @@ if __name__ == "__main__":
                     k.strip(),
                     {v.strip() for v in vs.split(',')})
                 )(*x.split('=', 1)),
-            help="Only include results where this field is this value.")
+            help="Only include results where this field is this value. May "
+                "include comma-separated options and globs.")
     parser.add_argument(
             '-L', '--add-label',
             dest='labels',
diff --git a/scripts/treemapd3.py b/scripts/treemapd3.py
index ec4ff005..548e49cf 100755
--- a/scripts/treemapd3.py
+++ b/scripts/treemapd3.py
@@ -104,7 +104,9 @@ def collect(csv_paths, defines=[]):
                             if k not in fields)
                 for r in reader:
                     # filter by matching defines
-                    if not all(k in r and r[k] in vs for k, vs in defines):
+                    if not all(any(fnmatch.fnmatchcase(r.get(k, ''), v)
+                                for v in vs)
+                            for k, vs in defines):
                         continue
 
                     results.append(r)
@@ -118,7 +120,9 @@ def fold(results, by=None, fields=None, defines=[]):
     if defines:
         results_ = []
         for r in results:
-            if all(k in r and r[k] in vs for k, vs in defines):
+            if all(any(fnmatch.fnmatchcase(r.get(k, ''), v)
+                        for v in vs)
+                    for k, vs in defines):
                 results_.append(r)
         results = results_
 
@@ -1043,7 +1047,8 @@ if __name__ == "__main__":
                     k.strip(),
                     {v.strip() for v in vs.split(',')})
                 )(*x.split('=', 1)),
-            help="Only include results where this field is this value.")
+            help="Only include results where this field is this value. May "
+                "include comma-separated options and globs.")
     parser.add_argument(
             '-L', '--add-label',
             dest='labels',