gregchapman-dev
diff --git a/‎.pylintrc‎
Lines changed: 1 addition & 0 deletions b/‎.pylintrc‎
Lines changed: 1 addition & 0 deletions
diff --git a/‎LICENSE‎
Lines changed: 1 addition & 1 deletion b/‎LICENSE‎
Lines changed: 1 addition & 1 deletion
diff --git a/‎README.md‎
Lines changed: 5 additions & 4 deletions b/‎README.md‎
Lines changed: 5 additions & 4 deletions
diff --git a/‎ReleaseNotes_4.1.0.txt‎
Lines changed: 34 additions & 0 deletions b/‎ReleaseNotes_4.1.0.txt‎
Lines changed: 34 additions & 0 deletions
diff --git a/‎musicdiff/__init__.py‎
Lines changed: 40 additions & 12 deletions b/‎musicdiff/__init__.py‎
Lines changed: 40 additions & 12 deletions
diff --git a/‎musicdiff/__main__.py‎
Lines changed: 24 additions & 7 deletions b/‎musicdiff/__main__.py‎
Lines changed: 24 additions & 7 deletions
@@ -325,6 +325,7 @@ exclude-protected=_asdict,_fields,_replace,_source,_make
 
 # Maximum number of arguments for function / method
 max-args=5
+max-positional-arguments=10
 
 # maximum boolean expressions in a line (too-many-boolean-expressions)
 max-bool-expr=10
 
@@ -1,6 +1,6 @@
 
 The MIT License (MIT)
-Copyright (c) 2022-2024 Francesco Foscarin, Greg Chapman
+Copyright (c) 2022-2025 Francesco Foscarin, Greg Chapman
 
 Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
 
 
@@ -7,7 +7,7 @@ musicdiff is derived from: [music-score-diff](https://github.com/fosfrancesco/mu
     by [Francesco Foscarin](https://github.com/fosfrancesco).
 
 ## Setup
-Depends on [music21](https://pypi.org/project/music21) (version 9.1+),  [numpy](https://pypi.org/project/numpy), and [converter21](https://pypi.org/project/converter21) (version 3.2+). You also will need to configure music21 (instructions [here](https://web.mit.edu/music21/doc/usersGuide/usersGuide_01_installing.html)) to display a musical score (e.g. with MuseScore).  Requires Python 3.10+.
+Depends on [music21](https://pypi.org/project/music21) (version 9.1+),  [numpy](https://pypi.org/project/numpy), and [converter21](https://pypi.org/project/converter21) (version 3.3+). You also will need to configure music21 (instructions [here](https://web.mit.edu/music21/doc/usersGuide/usersGuide_01_installing.html)) to display a musical score (e.g. with MuseScore).  Requires Python 3.10+.
 
 ## Usage
 On the command line:
@@ -26,9 +26,10 @@ On the command line:
                     default this is ignored).
       -x/--exclude  one or more named details to exclude from comparison.  Can be any of the
                     named details accepted by -i/--include.
-      -o/--output   one or both of two output formats: text (or t) or visual (or v); the default
-                    is visual). visual (or v) requests production of marked-up score PDFs; text
-                    (or t) requests production of diff-like text output.
+      -o/--output   one or more of three output formats: text (or t) or visual (or v) or ser (or s);
+                    the default is visual). visual (or v) requests production of marked-up score
+                    PDFs; text (or t) requests production of diff-like text output; ser (or s)
+                    requests a JSON text output containing Symbolic Error Ratio information.
 
       file1         first music score file to compare (any format music21 or converter21 can parse)
       file2         second music score file to compare (any format music21 or converter21 can parse)
 
@@ -0,0 +1,34 @@
+Changes since 4.0.0:
+    Add new output option that prints JSON containing the symbolic error rate (SER =
+        numSymbolErrors / numSymbolsInGroundTruth) to stdout (the JSON actually
+        contains all three numbers).  Ground truth is assumed to be the second file.
+        If numSymbolsInGroundTruth == 0, SER will be numSymbolErrors, to avoid divide
+        by zero.
+    Add new API Visualization.get_ser_output() that returns a dict containing the
+        symbolic error rate.
+    In support of SER, notation_sizes (a.k.a. symbol counts) and diff costs (a.k.a.
+        symbolic error counts) have been reviewed and updated:
+        AnnNote.notation_size(): add 1 symbol for slash on grace note
+        AnnExtra.notation_size(): 1 symbol for the text, add 1 symbol if there is any
+            style specified
+        AnnExtra diff error count: text diff is 1 symbol error, offset diff is 1 symbol
+            error, duration diff is 1 symbol error, style diff is 1 symbol error
+        AnnLyric.notation_size(): use len(text) as symbol count instead of 1;
+            add 1 symbol if there's a verse number;
+            add 1 symbol if there's a verse identifier different from the number;
+            add 1 symbol if styled
+        AnnLyric diff cost: text diff symbol error count is the Levenshtein distance,
+            verse number diff is 1 symbol error,  verse identifier diff is 1 symbol
+            error, offset diff is 1 symbol error, style diff is 1 symbol error
+        AnnMeasure.notation_size(): not just notes' symbols and extras' symbols, add in
+            the lyrics' symbols
+        AnnScore.notation_size(): not just parts' symbols, add in staff_groups' symbols
+            and metadata_items' symbols
+    Add support for comparing scores that have different number of parts (this previously
+        caused a failure). The existing parts are assumed to line up by index (as before,
+        score1 part 0 is compared with score2 part 0), and then we generate edits that
+        either delete the extra parts in score1, or add the extra parts in score2. The
+        number of symbol errors for those edits is simply the notation_size of (the
+        number of symbols in) the added or deleted parts.
+    Several smallish bugfixes.
+
@@ -14,6 +14,7 @@
 
 import sys
 import os
+import json
 import typing as t
 from pathlib import Path
 
@@ -52,6 +53,8 @@ def diff(
     force_parse: bool = True,
     visualize_diffs: bool = True,
     print_text_output: bool = False,
+    print_ser_output: bool = False,
+    fix_first_file_syntax: bool = False,
     detail: DetailLevel | int = DetailLevel.Default
 ) -> int | None:
     '''
@@ -77,6 +80,16 @@ def diff(
         visualize_diffs (bool): Whether or not to render diffs as marked up PDFs. If False,
             the only result of the call will be the return value (the number of differences).
             (default is True)
+        print_text_output (bool): Whether or not to print diffs in diff-like text to stdout.
+            (default is False)
+        print_ser_output (bool): Whether or not to print the symbolic error rate (SER),
+            which is computed as number of symbolic errors divided by the max number of
+            symbols in the two scores.
+            (default is False)
+        fix_first_file_syntax (bool): Whether to attempt to fix syntax errors in the first
+            file (and add the number of such fixes to the returned number of edits/cost in
+            symbol errors).
+            (default is False)
         detail (DetailLevel | int): What level of detail to use during the diff.
             Can be DecoratedNotesAndRests, OtherObjects, AllObjects, Default (currently
             AllObjects), or any combination (with | or &~) of those or NotesAndRests,
@@ -85,8 +98,9 @@ def diff(
             Style, Metadata, or Voicing.
 
     Returns:
-        int | None: The number of differences found (0 means the scores were identical,
-            None means the diff failed)
+        int | None: The total cost of the edits, i.e. the number of individual symbols
+            that must be added or deleted. (0 means that the scores were identical, and
+            None means that one or more of the input files failed to parse.)
     '''
     # Use the Humdrum/MEI importers from converter21 in place of the ones in music21...
     # Comment out this line to go back to music21's built-in Humdrum/MEI importers.
@@ -130,7 +144,11 @@ def diff(
         if not badArg1:
             # pylint: disable=broad-except
             try:
-                sc = m21.converter.parse(score1, forceSource=force_parse)
+                sc = m21.converter.parse(
+                    score1,
+                    forceSource=force_parse,
+                    acceptSyntaxErrors=fix_first_file_syntax
+                )
                 if t.TYPE_CHECKING:
                     assert isinstance(sc, m21.stream.Score)
                 score1 = sc
@@ -176,11 +194,10 @@ def diff(
     annotated_score2: AnnScore = AnnScore(score2, detail)
 
     diff_list: list
-    _cost: int
-    diff_list, _cost = Comparison.annotated_scores_diff(annotated_score1, annotated_score2)
+    cost: int
+    diff_list, cost = Comparison.annotated_scores_diff(annotated_score1, annotated_score2)
 
-    numDiffs: int = len(diff_list)
-    if numDiffs != 0:
+    if cost != 0:
         if visualize_diffs:
             # you can change these three colors as you like...
             # Visualization.INSERTED_COLOR = 'red'
@@ -194,10 +211,21 @@ def diff(
             # 'score1 ' and 'score2 ', respectively, so you can see which is which.
             Visualization.show_diffs(score1, score2, out_path1, out_path2)
 
-        if print_text_output:
-            text_output: str = Visualization.get_text_output(
-                score1, score2, diff_list, score1Name=score1Name, score2Name=score2Name
-            )
+    if print_ser_output:
+        ser_output: dict = Visualization.get_ser_output(
+            cost, annotated_score2
+        )
+        jsonStr: str = json.dumps(ser_output, indent=4)
+        print(jsonStr)
+
+    if print_text_output:
+        text_output: str = Visualization.get_text_output(
+            score1, score2, diff_list, score1Name=score1Name, score2Name=score2Name
+        )
+        if text_output:
+            if print_ser_output and print_text_output:
+                # put a blank line between them
+                print('')
             print(text_output)
 
-    return numDiffs
+    return cost
@@ -106,10 +106,23 @@
         "--output",
         default=["visual"],
         nargs="*",
-        choices=["visual", "v", "text", "t"],
+        choices=["visual", "v", "text", "t", "ser", "s"],
         help="'visual'/'v' is marked up scores, rendered to PDFs;"
-        + " 'text'/'t' is diff-like, written to stdout."
-        + " Either, both, or neither can be requested."
+        + " 'text'/'t' is diff-like, written to stdout;"
+        + " 'ser'/'s is the symbolic error rate (symbol errors/total symbols),"
+        + " written to stdout."
+        + " Any, all, or none of these can be requested."
+    )
+
+    parser.add_argument(
+        "--fix_first_file_syntax",
+        action='store_true',
+        help="If set, syntax errors in the first input file will be fixed"
+        + " (if possible) so the diff can continue. Any fixes will be"
+        + " added to the returned cost in symbol errors). Note that errors"
+        + " in the second file (assumed to be the ground truth) are never"
+        + " corrected.  Note also that this currently only works for Humdrum"
+        + " **kern files."
     )
 
     args = parser.parse_args()
@@ -222,16 +235,20 @@
 
     visualize_diffs: bool = "visual" in args.output or "v" in args.output
     print_text_output: bool = "text" in args.output or "t" in args.output
+    print_ser_output: bool = "ser" in args.output or "s" in args.output
+    fix_first_file_syntax: bool = args.fix_first_file_syntax is True
 
-    numDiffs: int | None = diff(
+    cost: int | None = diff(
         args.file1,
         args.file2,
         detail=detail,
         visualize_diffs=visualize_diffs,
-        print_text_output=print_text_output
+        print_text_output=print_text_output,
+        print_ser_output=print_ser_output,
+        fix_first_file_syntax=fix_first_file_syntax,
     )
 
-    if numDiffs is None:
+    if cost is None:
         print('musicdiff failed.', file=sys.stderr)
-    elif numDiffs == 0:
+    elif cost == 0:
         print(f'Scores in {args.file1} and {args.file2} are identical.', file=sys.stderr)