inspectr 0.0.4__py3-none-any.whl → 0.1.0__py3-none-any.whl

inspectr/count_exceptions.py

@@ -5,7 +5,16 @@ from collections import Counter, defaultdict
 from typing import List
 
 
-def main(files: List[pathlib.Path]) -> None:
+def main(files: List[pathlib.Path], **kwargs) -> None:
+    for f in files:
+        if not f.exists():
+            print(f"Error: File does not exist: {f}")
+            return
+        
+        if not f.is_file():
+            print(f"Error: Not a file: {f}")
+            return
+
     exception_types = Counter()
     bare_or_exception_per_file = defaultdict(int)
 

inspectr/duplicates.py

@@ -1,6 +1,130 @@
 import sys
-import hashlib
+import pathlib
 from collections import defaultdict
+from typing import List, Tuple
+
+
+def calculate_similarity(lines1: List[str], lines2: List[str]) -> float:
+    if not lines1 or not lines2:
+        return 0.0
+    matches = sum(1 for a, b in zip(lines1, lines2) if a == b)
+    return matches / max(len(lines1), len(lines2))
+
+
+def ranges_overlap(start1, end1, start2, end2):
+    """Check if two ranges overlap by more than 50%"""
+    overlap_start = max(start1, start2)
+    overlap_end = min(end1, end2)
+    
+    if overlap_start >= overlap_end:
+        return False
+    
+    overlap_size = overlap_end - overlap_start
+    range1_size = end1 - start1
+    range2_size = end2 - start2
+    
+    overlap_pct1 = overlap_size / range1_size if range1_size > 0 else 0
+    overlap_pct2 = overlap_size / range2_size if range2_size > 0 else 0
+    
+    return overlap_pct1 > 0.5 or overlap_pct2 > 0.5
+
+
+def merge_overlapping_groups(groups, block_size, file_lines):
+    """Merge groups that have overlapping ranges by more than 50%, recompute similarity after merging"""
+    if not groups:
+        return []
+    
+    groups_by_file = defaultdict(list)
+    for fname, lnum, similar_blocks in groups:
+        groups_by_file[fname].append((lnum, similar_blocks))
+    
+    merged_groups = []
+    
+    for fname, file_groups in groups_by_file.items():
+        file_groups.sort(key=lambda x: x[0])
+        
+        current_start = file_groups[0][0]
+        current_end = current_start + block_size - 1
+        current_similar_dict = {}
+        
+        for f, l, s in file_groups[0][1]:
+            end = l + block_size - 1
+            key = f
+            if key not in current_similar_dict:
+                current_similar_dict[key] = []
+            current_similar_dict[key].append((l, end))
+        
+        for i in range(1, len(file_groups)):
+            lnum, similar_blocks = file_groups[i]
+            end_line = lnum + block_size - 1
+            
+            if ranges_overlap(current_start, current_end, lnum, end_line):
+                current_end = max(current_end, end_line)
+                
+                for f, l, s in similar_blocks:
+                    end = l + block_size - 1
+                    key = f
+                    if key not in current_similar_dict:
+                        current_similar_dict[key] = []
+                    current_similar_dict[key].append((l, end))
+            else:
+                actual_size = current_end - current_start + 1
+                merged_similar = compute_merged_similarities(
+                    fname, current_start, current_end,
+                    current_similar_dict, file_lines
+                )
+                merged_groups.append((fname, current_start, actual_size, merged_similar))
+                
+                current_start = lnum
+                current_end = end_line
+                current_similar_dict = {}
+                for f, l, s in similar_blocks:
+                    end = l + block_size - 1
+                    key = f
+                    if key not in current_similar_dict:
+                        current_similar_dict[key] = []
+                    current_similar_dict[key].append((l, end))
+        
+        actual_size = current_end - current_start + 1
+        merged_similar = compute_merged_similarities(
+            fname, current_start, current_end,
+            current_similar_dict, file_lines
+        )
+        merged_groups.append((fname, current_start, actual_size, merged_similar))
+    
+    return merged_groups
+
+
+def compute_merged_similarities(fname, start, end, similar_dict, file_lines):
+    """Compute similarity for merged ranges"""
+    merged_similar = []
+    
+    if fname not in file_lines:
+        return merged_similar
+    
+    primary_lines = file_lines[fname][start - 1:end]
+    
+    for other_file, ranges in similar_dict.items():
+        if other_file not in file_lines:
+            continue
+        
+        ranges.sort()
+        merged_ranges = []
+        
+        for range_start, range_end in ranges:
+            if merged_ranges and ranges_overlap(merged_ranges[-1][0], merged_ranges[-1][1], range_start, range_end):
+                prev_start, prev_end = merged_ranges[-1]
+                merged_ranges[-1] = (min(prev_start, range_start), max(prev_end, range_end))
+            else:
+                merged_ranges.append((range_start, range_end))
+        
+        for merged_start, merged_end in merged_ranges:
+            other_lines = file_lines[other_file][merged_start - 1:merged_end]
+            similarity = calculate_similarity(primary_lines, other_lines)
+            merged_similar.append((other_file, merged_start, similarity))
+    
+    return merged_similar
+
 
 def find_duplicates(files, block_size=10, min_occur=3):
     """
@@ -12,39 +136,82 @@ def find_duplicates(files, block_size=10, min_occur=3):
         min_occur: minimum number of occurrences to report
 
     Yields:
-        (filename, line_number, count)
+        (primary_filename, primary_line, actual_block_size, [(other_file, other_line, similarity), ...])
     """
-    blocks = defaultdict(list)  # hash -> list of (file, line)
-
+    file_lines = {}
     for fname in files:
         try:
             with open(fname, encoding="utf-8") as f:
-                lines = f.readlines()
+                file_lines[fname] = f.readlines()
         except OSError as e:
             print(f"Could not read {fname}: {e}", file=sys.stderr)
             continue
 
+    all_blocks = []
+    for fname in file_lines:
+        lines = file_lines[fname]
         for i in range(len(lines) - block_size + 1):
-            # join block of lines
-            block = "".join(lines[i:i + block_size])
-            # stable hash
-            h = hashlib.sha1(block.encode("utf-8")).hexdigest()
-            blocks[h].append((fname, i + 1))
+            block_lines = lines[i:i + block_size]
+            all_blocks.append((fname, i + 1, block_lines))
 
-    for locs in blocks.values():
-        if len(locs) >= min_occur:
-            for fname, lnum in locs:
-                yield fname, lnum, len(locs)
+    reported = set()
+    groups = []
 
+    for i, (fname1, lnum1, block1) in enumerate(all_blocks):
+        key1 = (fname1, lnum1)
+        
+        if key1 in reported:
+            continue
+        
+        similar_blocks = []
+        
+        for j, (fname2, lnum2, block2) in enumerate(all_blocks):
+            if i >= j:
+                continue
+            
+            key2 = (fname2, lnum2)
+            if key2 in reported:
+                continue
+            
+            similarity = calculate_similarity(block1, block2)
+            if similarity > 0.8:
+                similar_blocks.append((fname2, lnum2, similarity))
+                reported.add(key2)
+        
+        if len(similar_blocks) + 1 >= min_occur:
+            reported.add(key1)
+            groups.append((fname1, lnum1, similar_blocks))
+    
+    merged = merge_overlapping_groups(groups, block_size, file_lines)
+    
+    for fname, lnum, actual_size, similar_blocks in merged:
+        yield fname, lnum, actual_size, similar_blocks
 
-def main(args=None) -> None:
-    if args is None:
-        args = sys.argv[1:]
 
-    if not args:
-        print("Usage: inspectr duplicates file1.py [file2.py ...]")
+def main(files: List[pathlib.Path], block_size: int = 10, min_occur: int = 3) -> None:
+    for f in files:
+        if not f.exists():
+            print(f"Error: File does not exist: {f}")
+            return
+        
+        if not f.is_file():
+            print(f"Error: Not a file: {f}")
+            return
+    
+    if not files:
+        print("Usage: inspectr duplicates [--block-size N] [--min-occur N] file1.py [file2.py ...]")
         return
 
-    for fname, lnum, count in find_duplicates(args, block_size=10, min_occur=3):
-        print(f"{fname}:{lnum}  (occurs {count} times)")
+    file_paths = [str(f) for f in files]
+    for fname, lnum, block_sz, similar_blocks in find_duplicates(file_paths, block_size=block_size, min_occur=min_occur):
+        end_line = lnum + block_sz - 1
+        output_parts = [f"{fname}: lines {lnum}-{end_line} occur in"]
+        
+        for other_file, other_line, similarity in similar_blocks:
+            other_end = other_line + block_sz - 1
+            similarity_pct = int(similarity * 100)
+            output_parts.append(f" {other_file} at lines {other_line}-{other_end} ({similarity_pct}% similarity) and")
+        
+        output = "".join(output_parts).rstrip(" and")
+        print(output)
 

inspectr/size_counts.py

@@ -11,7 +11,16 @@ FUNC_PARAMS = 5
 CLASS_METHODS = 20
 
 
-def main(files: List[pathlib.Path]) -> None:
+def main(files: List[pathlib.Path], **kwargs) -> None:
+    for f in files:
+        if not f.exists():
+            print(f"Error: File does not exist: {f}")
+            return
+        
+        if not f.is_file():
+            print(f"Error: Not a file: {f}")
+            return
+
     # TODO: rename these
     # Counters and diagnostics
     files_over_1000 = []

inspectr/with_open.py

@@ -4,11 +4,20 @@ import sys
 from typing import List
 
 
-def main(files: List[pathlib.Path]) -> None:
+def main(files: List[pathlib.Path], **kwargs) -> None:
     if not files:
         print("Usage: inspectr with_open <file1> [file2 ...]")
         sys.exit(1)
 
+    for f in files:
+        if not f.exists():
+            print(f"Error: File does not exist: {f}")
+            return
+        
+        if not f.is_file():
+            print(f"Error: Not a file: {f}")
+            return
+
     for filepath in files:
         tree = ast.parse(filepath.read_text(), filename=str(filepath))
         for node in ast.walk(tree):

{inspectr-0.0.4.dist-info → inspectr-0.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: inspectr
-Version: 0.0.4
+Version: 0.1.0
 Summary: A collection of python tools to inspect code quality. 
 Maintainer-email: Alex Mueller <amueller474@gmail.com>
 License-Expression: Apache-2.0
@@ -14,6 +14,9 @@ Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Topic :: Software Development
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: colorama
+Provides-Extra: test
+Requires-Dist: pytest; extra == "test"
 Dynamic: license-file
 
 # inspectr
@@ -29,15 +32,48 @@ pip install inspectr
 ## Usage
 Generally, the syntax goes:
 ```bash
-inspectr <subtool> [files...]
+inspectr <subtool> [options] [files...]
 ```
 where `<subtool>` is one of the following:
 
 - `authenticity`: looks for TODO comments, empty try/except blocks, and stub functions
 - `bare_ratio`: checks for the ratio of bare excepts to meaningful exception usage
+- `compare_funcs`: compares function/method names across two directory versions
+- `complexity`: analyzes algorithmic complexity of Python code
 - `count_exceptions`: counts how many of each type of exception there are (including bare except)
+- `duplicates`: looks for occurrences of duplicate or similar code (>80% similarity, default: 10+ lines, 3+ occurrences)
 - `size_counts`: various linecount-related code complexity checks
 - `with_open`: checks for `open` in the absense of `with` and manual calls to `close()`
 
+### Command-Line Options
+All tools accept command-line options in the format `--option-name value`. 
+Options are passed as keyword arguments to the tool's main function. For example:
+```bash
+inspectr duplicates --block-size 15 --min-occur 2 file1.py file2.py
+```
+
+Recognized options include:
+- `duplicates`:
+  - `--block-size N`: number of consecutive lines in a block (default: 10)
+  - `--min-occur N`: minimum number of occurrences to report (default: 3
+
+**Note**: any unrecognized options will be silently ignored.
+
+### Usage for compare_funcs
+The `compare_funcs` tool compares functions across two directory versions:
+```bash
+inspectr compare_funcs files_list.txt dir1 dir2
+```
+where `files_list.txt` contains relative paths to compare, one per line.
+
+## Local Testing
+First install in development mode with test dependencies, then run the tests:
+```bash
+git clone https://github.com/ajcm474/inspectr.git
+cd inspectr
+pip install -e ".[test]"
+pytest tests/
+```
+
 **Please note:** this project is in the early alpha stage, so don't expect the above subtool names 
 to be stable between versions. I might even merge/split them at some point.

inspectr-0.1.0.dist-info/RECORD

@@ -0,0 +1,16 @@
+inspectr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+inspectr/__main__.py,sha256=-BF-0Mi7-JjNabGSUPJ6IHu21EoNO0j0-jKd3wgnoDQ,1395
+inspectr/authenticity.py,sha256=GMM82Ol0Gn_Ol5W0C9UWsT3U7g1vNCRv30_oz-1gX-Q,2791
+inspectr/bare_ratio.py,sha256=lJ0cKToUy9y4hfcwCt2D1_-U0XI-j35gCTIgsbxgXBk,2229
+inspectr/compare_funcs.py,sha256=PHXV4XsrsPbfT_gAPi7HYPfljfZSJTCxpI13m3n8Gxg,3863
+inspectr/complexity.py,sha256=ewl7SccHgD5uBJi7z9n4I6rNFbHEz1rvZDqvjQN_IpM,30887
+inspectr/count_exceptions.py,sha256=Fpfq2Uyozg8rmc9fS_PAzB4WGDuzONKOjYUcbALrGwc,1820
+inspectr/duplicates.py,sha256=iam-p8pA_LuYxWJ0p3wbWsGX2EYTqHGdkyLuzfw1MEM,7721
+inspectr/size_counts.py,sha256=q0YZytb30XivT6W4B2HDxh2tWDox1B4Iz8VesIq7a6Y,3152
+inspectr/with_open.py,sha256=ekcdVeLQT0SEt3bMpxRWoJDXO8hdctArRdWkKliLes8,838
+inspectr-0.1.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+inspectr-0.1.0.dist-info/METADATA,sha256=TBsPAavCdBfCjj6s89BFSfTgVahkx54ad4W_pON4Bi0,2896
+inspectr-0.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+inspectr-0.1.0.dist-info/entry_points.txt,sha256=IrOM4SpCRfFZzBWngg3ezXuX31ZqFBR-flSU5c8tbTo,52
+inspectr-0.1.0.dist-info/top_level.txt,sha256=NlTFBMaWgYmxFzjQtp4Y6itVQQV8sBPtAAZvFnviT-A,9
+inspectr-0.1.0.dist-info/RECORD,,

inspectr-0.0.4.dist-info/RECORD

@@ -1,14 +0,0 @@
-inspectr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-inspectr/__main__.py,sha256=Rojob_KTdzcHjItkGgA3TPLqPd223pIfeajpCWDP3Gc,652
-inspectr/authenticity.py,sha256=fgKJSE_1qYE1NgLdXmOjPQjo-dwD42sEhqpcsazIj3U,1703
-inspectr/bare_ratio.py,sha256=oQfag96zjGnmFHofZ5qabBGGVoKUnmRNzGq_WX_8ZZg,1997
-inspectr/count_exceptions.py,sha256=UhUc3ZZY8eDxLtlLX1USKzP_JEPY3clx8R8TPvtQ5LE,1588
-inspectr/duplicates.py,sha256=xAFNO90JVEhzZqmyHg8gXAo28e_DIrB3SYh7tONAzbU,1455
-inspectr/size_counts.py,sha256=Yw-k5v7lPylzfh-9SUs1PtlV3Bhvdy9X7w2Pi93xL9g,2920
-inspectr/with_open.py,sha256=qbCAb14cZ15yX7SbLo2C3nE1sDEKLiZ48bvFQfTAKJk,606
-inspectr-0.0.4.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-inspectr-0.0.4.dist-info/METADATA,sha256=2YAiL5P6MPWIgR54rlkZXzt3fXxaW6CsT1vT1krn_uo,1573
-inspectr-0.0.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-inspectr-0.0.4.dist-info/entry_points.txt,sha256=IrOM4SpCRfFZzBWngg3ezXuX31ZqFBR-flSU5c8tbTo,52
-inspectr-0.0.4.dist-info/top_level.txt,sha256=NlTFBMaWgYmxFzjQtp4Y6itVQQV8sBPtAAZvFnviT-A,9
-inspectr-0.0.4.dist-info/RECORD,,