pseek 3.6.2__tar.gz → 3.7.0__tar.gz

{pseek-3.6.2 → pseek-3.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pseek
-Version: 3.6.2
+Version: 3.7.0
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
@@ -51,6 +51,7 @@ Fast and powerful command-line search tool for finding files, directories, and t
     * [Fuzzy](#fuzzy-search)
         * [Fuzzy Similarity Threshold](#fuzzy-similarity-threshold)
     * [Full Path](#full-path)
+    * [Line](#line)
 * [Expression Queries](#expression-queries)
     * [Operators](#supported-operators)
         * [AND](#and)
@@ -63,6 +64,7 @@ Fast and powerful command-line search tool for finding files, directories, and t
         * [Whole Word](#whole-word)
         * [Fuzzy](#fuzzy)
         * [Full Path](#full-path-1)
+        * [Line](#line-1)
         * [Combined Prefixes](#combined-prefixes)
 * [Automatic Filtering](#automatic-filtering)
 * [Manual Filtering](#manual-filtering)
@@ -215,6 +217,7 @@ psk --exclude build
 | `--expr` | Enable boolean query expressions. Example: `r"foo.*bar" and ("bar" or "baz") and not "qux"`. Prefixes: `r=regex`, `c=case-sensitive`, `w=whole-word`, `f=fuzzy` |
 | `--context` | Show N context lines before and after matches, or use N:M to specify before:after |
 | `--full-path` | By default, query is only matched against the filename or directory name (this applies only when searching for files or directories, not file contents). Using this flag, query is matched against the full path (and, if `--absolute-path` flag is enabled, against the absolute path) |
+| `--line` | Match lines where the entire line participates in a match |
 | `--depth` | Limit directory traversal to given depth range. By default, there is no limit on search depth |
 | `--timeout` | Stop the search after the specified number of seconds |
 | `--fuzzy` | Enable fuzzy search (Highlighting and counting matches are disabled in this mode if `--word` is not enabled to prevent the program from slowing down). except when `--expr` is enabled, in which case you can make it fuzzy by putting `f` before term: `f"foo"` |
@@ -399,6 +402,39 @@ With `--full-path`, you can match `fd/f` against the entry `fd/file.txt` inside
 
 > **Note:** For ordinary queries without `--regex`, backslashes are treated literally, so Windows paths can be searched without additional escaping. When using `--expr`, quoted terms use JSON-style escaping; escape backslashes accordingly. For example, `"\\"` represents a single literal backslash, while `"\\n"` represents the literal sequence `\n`.
 
+### Line
+
+Match the entire line or selected path instead of matching a pattern anywhere within it.
+
+```bash
+# Match lines exactly equal to "TODO"
+psk TODO --line
+
+# Match only lines containing exactly "foo" or "bar"
+psk 'foo|bar' --regex --line
+
+# Match files whose names are exactly "cli.py"
+psk "cli.py" --file --line
+```
+
+> **Note:** If both options are specified, `--line` takes precedence over `--word`. In this case, instead of checking individual word boundaries, the entire line or selected path is matched.
+
+By default, Pseek matches a file's or directory's **name**. Use `--full-path` to match against its full path instead.
+
+```bash
+# Match files named "cli.py"
+psk "cli.py" --file --line
+
+# Match the full relative path "pseek/cli.py"
+psk "pseek/cli.py" --file --full-path --line
+
+# Match the full absolute path
+psk "/home/python/cli/pseek/utils.py" \
+    --file --full-path --absolute-path --line
+```
+
+> **Note:** Leading and trailing whitespace is significant. `--line` does not trim the target before matching. Use an appropriate regular expression, such as `\s*TODO\s*` with `--line`, if surrounding whitespace should be ignored.
+
 ## Expression Queries
 
 Expression mode enables logical search expressions.
@@ -453,9 +489,7 @@ Each term can have its own search mode.
 
 #### Regex
 
-```text
-r"pattern"
-```
+Usage: `r"pattern"`
 
 Example:
 
@@ -465,9 +499,7 @@ psk 'r"error\d+"' --expr
 
 #### Case Sensitive
 
-```text
-c"text"
-```
+Usage: `c"text"`
 
 Example:
 
@@ -477,9 +509,7 @@ psk 'c"Error"' --expr
 
 #### Whole Word
 
-```text
-w"text"
-```
+Usage: `w"text"`
 
 Example:
 
@@ -489,9 +519,7 @@ psk 'w"cat"' --expr
 
 #### Fuzzy
 
-```text
-f"text"
-```
+Usage: `f"text"`
 
 Example:
 
@@ -501,9 +529,7 @@ psk 'f"apple"' --expr
 
 #### Full Path
 
-```text
-p"text"
-```
+Usage: `p"text"`
 
 Example:
 
@@ -511,6 +537,16 @@ Example:
 psk 'p"lib"' --expr
 ```
 
+#### Line
+
+Usage: `l"text"`
+
+Example:
+
+```bash
+psk 'l"foo"' --expr
+```
+
 #### Combined Prefixes
 
 Prefixes can be combined.
@@ -538,9 +574,7 @@ Meaning:
 
 simultaneously.
 
-Allowed modes: `r`, `c`, `w`, `f`, `p`, `rp`, `pc`, `wp`, `fp`, `rc`, `cw`, `cf`, `wf`, `cwf`, `rcp`, `cwp`, `cfp`, `wfp`, `cwfp`
-
-and their permutations.
+All modes are permitted, except for those where regex and word, or regex and fuzzy, are used simultaneously.
 
 > **Note:** Whole word matching and regex matching cannot be used at the same time, because we can use `\b` in regex to enable whole word matching: `r"\btext\b"`
 

{pseek-3.6.2 → pseek-3.7.0}/README.md

@@ -23,6 +23,7 @@ Fast and powerful command-line search tool for finding files, directories, and t
     * [Fuzzy](#fuzzy-search)
         * [Fuzzy Similarity Threshold](#fuzzy-similarity-threshold)
     * [Full Path](#full-path)
+    * [Line](#line)
 * [Expression Queries](#expression-queries)
     * [Operators](#supported-operators)
         * [AND](#and)
@@ -35,6 +36,7 @@ Fast and powerful command-line search tool for finding files, directories, and t
         * [Whole Word](#whole-word)
         * [Fuzzy](#fuzzy)
         * [Full Path](#full-path-1)
+        * [Line](#line-1)
         * [Combined Prefixes](#combined-prefixes)
 * [Automatic Filtering](#automatic-filtering)
 * [Manual Filtering](#manual-filtering)
@@ -187,6 +189,7 @@ psk --exclude build
 | `--expr` | Enable boolean query expressions. Example: `r"foo.*bar" and ("bar" or "baz") and not "qux"`. Prefixes: `r=regex`, `c=case-sensitive`, `w=whole-word`, `f=fuzzy` |
 | `--context` | Show N context lines before and after matches, or use N:M to specify before:after |
 | `--full-path` | By default, query is only matched against the filename or directory name (this applies only when searching for files or directories, not file contents). Using this flag, query is matched against the full path (and, if `--absolute-path` flag is enabled, against the absolute path) |
+| `--line` | Match lines where the entire line participates in a match |
 | `--depth` | Limit directory traversal to given depth range. By default, there is no limit on search depth |
 | `--timeout` | Stop the search after the specified number of seconds |
 | `--fuzzy` | Enable fuzzy search (Highlighting and counting matches are disabled in this mode if `--word` is not enabled to prevent the program from slowing down). except when `--expr` is enabled, in which case you can make it fuzzy by putting `f` before term: `f"foo"` |
@@ -371,6 +374,39 @@ With `--full-path`, you can match `fd/f` against the entry `fd/file.txt` inside
 
 > **Note:** For ordinary queries without `--regex`, backslashes are treated literally, so Windows paths can be searched without additional escaping. When using `--expr`, quoted terms use JSON-style escaping; escape backslashes accordingly. For example, `"\\"` represents a single literal backslash, while `"\\n"` represents the literal sequence `\n`.
 
+### Line
+
+Match the entire line or selected path instead of matching a pattern anywhere within it.
+
+```bash
+# Match lines exactly equal to "TODO"
+psk TODO --line
+
+# Match only lines containing exactly "foo" or "bar"
+psk 'foo|bar' --regex --line
+
+# Match files whose names are exactly "cli.py"
+psk "cli.py" --file --line
+```
+
+> **Note:** If both options are specified, `--line` takes precedence over `--word`. In this case, instead of checking individual word boundaries, the entire line or selected path is matched.
+
+By default, Pseek matches a file's or directory's **name**. Use `--full-path` to match against its full path instead.
+
+```bash
+# Match files named "cli.py"
+psk "cli.py" --file --line
+
+# Match the full relative path "pseek/cli.py"
+psk "pseek/cli.py" --file --full-path --line
+
+# Match the full absolute path
+psk "/home/python/cli/pseek/utils.py" \
+    --file --full-path --absolute-path --line
+```
+
+> **Note:** Leading and trailing whitespace is significant. `--line` does not trim the target before matching. Use an appropriate regular expression, such as `\s*TODO\s*` with `--line`, if surrounding whitespace should be ignored.
+
 ## Expression Queries
 
 Expression mode enables logical search expressions.
@@ -425,9 +461,7 @@ Each term can have its own search mode.
 
 #### Regex
 
-```text
-r"pattern"
-```
+Usage: `r"pattern"`
 
 Example:
 
@@ -437,9 +471,7 @@ psk 'r"error\d+"' --expr
 
 #### Case Sensitive
 
-```text
-c"text"
-```
+Usage: `c"text"`
 
 Example:
 
@@ -449,9 +481,7 @@ psk 'c"Error"' --expr
 
 #### Whole Word
 
-```text
-w"text"
-```
+Usage: `w"text"`
 
 Example:
 
@@ -461,9 +491,7 @@ psk 'w"cat"' --expr
 
 #### Fuzzy
 
-```text
-f"text"
-```
+Usage: `f"text"`
 
 Example:
 
@@ -473,9 +501,7 @@ psk 'f"apple"' --expr
 
 #### Full Path
 
-```text
-p"text"
-```
+Usage: `p"text"`
 
 Example:
 
@@ -483,6 +509,16 @@ Example:
 psk 'p"lib"' --expr
 ```
 
+#### Line
+
+Usage: `l"text"`
+
+Example:
+
+```bash
+psk 'l"foo"' --expr
+```
+
 #### Combined Prefixes
 
 Prefixes can be combined.
@@ -510,9 +546,7 @@ Meaning:
 
 simultaneously.
 
-Allowed modes: `r`, `c`, `w`, `f`, `p`, `rp`, `pc`, `wp`, `fp`, `rc`, `cw`, `cf`, `wf`, `cwf`, `rcp`, `cwp`, `cfp`, `wfp`, `cwfp`
-
-and their permutations.
+All modes are permitted, except for those where regex and word, or regex and fuzzy, are used simultaneously.
 
 > **Note:** Whole word matching and regex matching cannot be used at the same time, because we can use `\b` in regex to enable whole word matching: `r"\btext\b"`
 

{pseek-3.6.2 → pseek-3.7.0}/pseek/cli.py

@@ -347,6 +347,8 @@ def check_rar_backend(archive_enabled: bool, tool_path: str, backend: str):
               '(this applies only when searching for files or directories, not file contents). '
               'Using this flag, query is matched against the full path '
               '(and, if --absolute-path flag is enabled, against the absolute path).')
+@click.option('--line', is_flag=True,
+              help='Match lines where the entire line participates in a match.')
 @click.option('-D', '--depth', multiple=True, metavar='MIN:MAX',
               help='Limit directory traversal to given depth range. '
               'By default, there is no limit on search depth.')
@@ -440,10 +442,10 @@ def search(**kwargs):
 
     check_rar_backend(config.archive, config.rar_backend, config.query)
 
-    if not config.expr and config.fuzzy:
+    if not config.expr and config.fuzzy and not config.line:
         if not config.word:
             click.secho(
-                "Warning: Fuzzy substring highlighting and counting matches are disabled to improve performance.",
+                "Warning: To improve performance, highlighting of matches is disabled.",
                 fg="yellow"
             )
         elif config.word and " " in config.query:

{pseek-3.6.2 → pseek-3.7.0}/pseek/parser.py

@@ -26,7 +26,8 @@ class TermNode(ExprNode):
         case_sensitive: bool,
         fuzzy: bool,
         fuzzy_level: int | None,
-        full_path: bool
+        full_path: bool,
+        whole_line: bool
     ):
         self.raw_term = term
         self.term_lower = term.lower()
@@ -36,6 +37,7 @@ class TermNode(ExprNode):
         self.fuzzy = fuzzy
         self.fuzzy_level = fuzzy_level
         self.full_path = full_path
+        self.whole_line = whole_line
 
         if not fuzzy:
             flags = 0 if case_sensitive else re.IGNORECASE  # Adjust case sensitivity
@@ -44,7 +46,7 @@ class TermNode(ExprNode):
             if not regex:
                 term = re.escape(term)  # Escape if not regex
                 # Apply whole-word matching only if not using regex (or if desired behavior is defined)
-                if whole_word:
+                if whole_word and not whole_line:
                     term = r'\b' + term + r'\b'
 
             self.pattern = compile_regex(term, flags)  # Precompile the regex pattern for performance
@@ -60,20 +62,29 @@ class TermNode(ExprNode):
         if not self.fuzzy:
             # Use substring search for more speed
             if not self.regex and not self.whole_word:
+                if self.whole_line:
+                    return term == text_cmp
                 return term in text_cmp
 
-            return bool(self.pattern.search(text))
+            return bool(self.pattern.search(text)) \
+                if not self.whole_line \
+                else bool(self.pattern.fullmatch(text))
+
+        if self.whole_line:
+            score = fuzz.ratio(term, text_cmp)
+            return score >= self.fuzzy_level
 
         if self.whole_word:
             words = re.findall(r'\w+', text_cmp)
             return any(fuzz.ratio(term, word) >= self.fuzzy_level for word in words)
+
+        # Use the correct method depending on the len of str to increase accuracy and avoid illogical matching
+        if len(text_cmp) > len(term):
+            score = fuzz.partial_ratio(term, text_cmp)
         else:
-            # Use the correct method depending on the len of str to increase accuracy and avoid illogical matching
-            if len(text_cmp) > len(term):
-                score = fuzz.partial_ratio(term, text_cmp)
-            else:
-                score = fuzz.ratio(term, text_cmp)
-            return score >= self.fuzzy_level
+            score = fuzz.ratio(term, text_cmp)
+
+        return score >= self.fuzzy_level
 
     def get_binary_pattern(self):
         """
@@ -129,25 +140,8 @@ class OrNode(ExprNode):
         return self.left.evaluate(text) or self.right.evaluate(text)
 
 
-def gvp() -> str:
-    """Generate all possible states and permutations of input prefixes
-
-    Returns:
-        str: prefixes=("f", "r", "rf") -> result="f|r|rf|fr"
-    """
-
-    prefixes = {'r','c','w','f','p','rp','pc','wp','fp','rc','cw',
-                'cf','wf','cwf','rcp','cwp','cfp','wfp','cwfp'}
-    valid_prefixes = set()
-
-    for p in prefixes:
-        valid_prefixes |= {''.join(pr) for pr in permutations(p)}
-
-    return '|'.join(valid_prefixes)
-
-
 # Lark grammar for parsing logical expressions
-query_grammar = rf"""
+query_grammar = r"""
 ?start: expr
 
 ?expr: or_expr
@@ -165,7 +159,7 @@ query_grammar = rf"""
      | ESCAPED_STRING           -> string
      | "(" expr ")"
 
-PREFIXED_STRING: /({gvp()})"([^"\\]|\\.)*"/
+PREFIXED_STRING: /[rcwfpl]+"([^"\\]|\\.)*"/
 
 %import common.ESCAPED_STRING
 %import common.WS
@@ -204,6 +198,7 @@ class TreeToExpr(Transformer):
             False,
             False,
             None,
+            False,
             False
         )
 
@@ -213,6 +208,14 @@ class TreeToExpr(Transformer):
 
         quote_index = text.index('"')
         prefix = text[:quote_index]
+
+        if len(prefix) != len(set(prefix)):
+            raise ValueError(f'Duplicate prefix flag: {prefix}')
+        if 'r' in prefix and 'f' in prefix:
+            raise ValueError('Regex and fuzzy prefixes cannot be combined.')
+        if 'r' in prefix and 'w' in prefix:
+            raise ValueError('Regex and whole-word prefixes cannot be combined. To use whole-word matching in regex, use \\b: r"\\btext\\b"')
+
         quoted = text[quote_index:]
 
         is_regex = 'r' in prefix
@@ -225,7 +228,8 @@ class TreeToExpr(Transformer):
             case_sensitive='c' in prefix,
             fuzzy='f' in prefix,
             fuzzy_level=self.fuzzy_level,
-            full_path='p' in prefix
+            full_path='p' in prefix,
+            whole_line='l' in prefix
         )
 
     def and_expr(self, args):
@@ -238,7 +242,7 @@ class TreeToExpr(Transformer):
         return NotNode(args[0])
 
 
-def parse_query_expression(config) -> ExprNode:
+def parse_query_expression(config) -> ExprNode | None:
     """
     Function to parse the query and return expression tree.
     If expr is False, treat the whole query as a single term.
@@ -255,7 +259,8 @@ def parse_query_expression(config) -> ExprNode:
             config.case_sensitive,
             config.fuzzy,
             config.fuzzy_level,
-            config.full_path
+            config.full_path,
+            config.line
         )
 
     # Otherwise, parse using Lark
@@ -276,7 +281,7 @@ def find_term_matches(node: TermNode, text: str | Path, num: int) -> list[tuple[
 
     if node.fuzzy:
         # Fuzzy partial matching currently has no span extraction
-        if not node.whole_word:
+        if not node.whole_word and not node.whole_line:
             return []
 
         text_cmp = (
@@ -288,6 +293,11 @@ def find_term_matches(node: TermNode, text: str | Path, num: int) -> list[tuple[
             else node.term_lower
         )
 
+        if node.whole_line:
+            if fuzz.ratio(term, text_cmp) >= node.fuzzy_level:
+                return [(num, len(text) + num)]
+            return []
+
         matches = []
 
         for match in re.finditer(r'\w+', text_cmp):
@@ -301,6 +311,9 @@ def find_term_matches(node: TermNode, text: str | Path, num: int) -> list[tuple[
 
         return matches
 
+    if node.whole_line and node.pattern.fullmatch(text) is not None:
+        return [(num, len(text) + num)]
+
     return [
         (match.start() + num, match.end() + num)
         for match in node.pattern.finditer(text)

{pseek-3.6.2 → pseek-3.7.0}/pseek/structs.py

@@ -133,6 +133,7 @@ class SearchConfig:
     case_sensitive: bool
     regex: bool
     word: bool
+    line: bool
     expr: bool
     depth: list[tuple]
     timeout: int | None

{pseek-3.6.2 → pseek-3.7.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "maturin"
 
 [project]
 name = "pseek"
-version = "3.6.2"
+version = "3.7.0"
 description = "Pseek is a Python CLI toolkit to search files, folders, and text"
 readme = "README.md"
 license = "MIT"