pseek 3.6.1__tar.gz → 3.6.2__tar.gz

{pseek-3.6.1 → pseek-3.6.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pseek
-Version: 3.6.1
+Version: 3.6.2
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers

{pseek-3.6.1 → pseek-3.6.2}/pseek/archive.py

@@ -30,22 +30,16 @@ def get_archive_path_size(info, file_type: str) -> int:
 def archive_should_skip(path_info: Path, config, p_size: float, file_ext, is_dir=False):
     """Check whether the file/directory inside archive files should be skipped based on various filters"""
 
-    if (config.arc_include and not any(path_info.is_relative_to(inc) for inc in config.arc_include)) \
+    path_info_str = str(path_info)
+    return (config.arc_include and not any(path_info.is_relative_to(inc) for inc in config.arc_include)) \
             or (config.arc_exclude and any(path_info.is_relative_to(exc) for exc in config.arc_exclude)) \
             or (config.arc_ext and file_ext not in config.arc_ext) \
             or (config.arc_exc_ext and file_ext in config.arc_exc_ext) \
             or (config.arc_size and (is_dir or not any(
                 minimum <= p_size <= maximum
                 for minimum, maximum in config.arc_size
-            ))):
-        return True
-
-    if config.re_include:
-        return not config.re_include.search(str(path_info))
-    if config.re_exclude:
-        return config.re_exclude.search(str(path_info)) is not None
-
-    return False
+            ))) or (config.re_include and not config.re_include.search(path_info_str)) \
+        or (config.re_exclude and config.re_exclude.search(path_info_str) is not None)
 
 
 def extract_names_from_archive(file_path: Path, config, depth: int = -1,
@@ -78,8 +72,8 @@ def extract_names_from_archive(file_path: Path, config, depth: int = -1,
             with opener(file_stream) as f:
                 for info in f.infolist():
                     name = Path(info.filename)
-                    new_path_ext = get_path_suffix(name)
                     is_dir = info.is_dir()
+                    new_path_ext = get_path_suffix(name, is_dir)
 
                     if not archive_should_skip(
                             name,
@@ -105,8 +99,8 @@ def extract_names_from_archive(file_path: Path, config, depth: int = -1,
             with py7zr.SevenZipFile(file_stream, mode='r') as z:
                 for info in z.list():
                     name = Path(info.filename)
-                    new_path_ext = get_path_suffix(name)
                     is_dir = info.is_directory
+                    new_path_ext = get_path_suffix(name, is_dir)
 
                     if not archive_should_skip(
                             name,
@@ -143,8 +137,8 @@ def extract_names_from_archive(file_path: Path, config, depth: int = -1,
             with tarfile.open(fileobj=file_stream, mode=mode) as tf:
                 for member in tf.getmembers():
                     name = Path(member.name)
-                    new_path_ext = get_path_suffix(name)
                     is_dir = member.isdir()
+                    new_path_ext = get_path_suffix(name, is_dir)
 
                     if not archive_should_skip(
                             name,
@@ -203,10 +197,10 @@ def extract_text_from_archive(file_path: Path, config, depth: int = -1,
                 for info in f.infolist():
                     if info.is_dir():
                         continue
-                    
+
                     file_name = Path(info.filename)
                     new_path_ext = get_path_suffix(file_name)
-                    
+
                     if archive_should_skip(
                         file_name,
                         config,
@@ -243,7 +237,7 @@ def extract_text_from_archive(file_path: Path, config, depth: int = -1,
 
                     file_name = Path(info.filename)
                     new_path_ext = get_path_suffix(file_name)
-                    
+
                     if archive_should_skip(
                         file_name,
                         config,
@@ -282,7 +276,7 @@ def extract_text_from_archive(file_path: Path, config, depth: int = -1,
 
                     file_name = Path(member.name)
                     new_path_ext = get_path_suffix(file_name)
-                    
+
                     if archive_should_skip(
                         file_name,
                         config,

{pseek-3.6.1 → pseek-3.6.2}/pseek/searcher.py

@@ -306,41 +306,50 @@ def search_content(config, matches: dict, pattern, binary_pattern,
         return
 
     collector = ContextCollector(config.context)
-    # Memory-map the file for efficient access
-    with open(p, 'rb') as f, mmap.mmap(f.fileno(), 0, access=mmap.ACCESS_READ) as mm:
-        head = mm[:8192]
-        if is_binary(head) or (binary_pattern and not content_contains(mm, binary_pattern)):
-            return
+    try:
+        # Memory-map the file for efficient access
+        with open(p, 'rb') as f, mmap.mmap(f.fileno(), 0, access=mmap.ACCESS_READ) as mm:
+            head = mm[:8192]
+            if is_binary(head) or (binary_pattern and not content_contains(mm, binary_pattern)):
+                return
 
-        mm.seek(0)  # Move the cursor to the beginning of the file
+            mm.seek(0)  # Move the cursor to the beginning of the file
 
-        # Iterate over each line in the file
-        for num, line in enumerate(iter(mm.readline, b''), 1):
-            try:
-                line_decoded = line.decode('utf-8').rstrip('\r\n')
-            except UnicodeDecodeError:
-                # Skip lines that can't be decoded
-                continue
+            # Iterate over each line in the file
+            for num, line in enumerate(iter(mm.readline, b''), 1):
+                if binary_pattern and not content_contains(line, binary_pattern):
+                    continue
 
-            matched = pattern is None or pattern.evaluate(line_decoded)
+                try:
+                    line_decoded = line.decode('utf-8').rstrip('\r\n')
+                except UnicodeDecodeError:
+                    # Skip lines that can't be decoded
+                    continue
 
-            # Avoid searching through the entire file content if the paths-only flag is True
-            if config.paths_only and matched:
-                add_result(
-                    matches,
-                    result_queue,
-                    'content',
-                    ContentResult(path=path_str),
-                    result_lock
-                )
-                return
+                matched = pattern is None or pattern.evaluate(line_decoded)
 
-            line_instance = Line(num, line_decoded)
+                # Avoid searching through the entire file content if the paths-only flag is True
+                if config.paths_only and matched:
+                    add_result(
+                        matches,
+                        result_queue,
+                        'content',
+                        ContentResult(path=path_str),
+                        result_lock
+                    )
+                    return
 
-            if matched:
-                line_instance.matches = find_matches(pattern, line_decoded)
+                if not any(config.context) and not matched:
+                    continue
+
+                line_instance = Line(num, line_decoded)
+
+                if matched:
+                    line_instance.matches = find_matches(pattern, line_decoded)
 
-            collector.process(line_instance, matched)
+                collector.process(line_instance, matched)
+    except OSError:
+        return
 
     groups = collector.finish()
     if groups:

{pseek-3.6.1 → pseek-3.6.2}/pseek/utils.py

@@ -24,13 +24,19 @@ def compile_regex(txt, flags=0) -> re.Pattern | None:
             raise click.exceptions.Exit(1)
 
 
-def get_path_suffix(path: Path | str) -> str:
+def get_path_suffix(path: Path | str, is_dir: bool | None = None) -> str:
     """ If multiple file suffixes are valid, return them, otherwise return only the last suffix """
     if isinstance(path, str):
         path = Path(path)
 
-    if path.is_dir():
-        return None
+    # The paths within archive aren't physical paths,
+    # so we need to determine is_dir from their metadata.
+    if is_dir is not None:
+        if is_dir:
+            return None
+    else:
+        if path.is_dir():
+            return None
 
     suffixes = ''.join(path.suffixes)[1:].lower()
 

{pseek-3.6.1 → pseek-3.6.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "maturin"
 
 [project]
 name = "pseek"
-version = "3.6.1"
+version = "3.6.2"
 description = "Pseek is a Python CLI toolkit to search files, folders, and text"
 readme = "README.md"
 license = "MIT"