v1.1.0

bagheera_search_lib/__init__.py

@@ -1,7 +1,14 @@
-from .bagheera_search import BagheeraSearcher
+from .bagheera_search import (
+    BagheeraSearcher, EvaluateExpression
+)
 
 
 def search(query):
     """Interfaz simplificada para la librería."""
     bs = BagheeraSearcher()
     return bs.search(query)
+
+
+def create_evaluator(expression):
+    ee = EvaluateExpression()
+    return ee.compile(expression)

bagheera_search_lib/bagheera_search.py

@@ -10,9 +10,136 @@ import sys
 from pathlib import Path
 from typing import Dict, Any, Iterator, Optional, Union
 
-from baloo_tools import get_resolution
+from baloo_tools import (get_info, get_tags)
 from bagheera_query_parser_lib import parse_date
 
+from pyparsing import (
+    alphanums, one_of, infix_notation,
+    Group, opAssoc, ParserElement, QuotedString, Word
+)
+
+ParserElement.enable_packrat()
+
+
+def expression_contains_property(text):
+    pattern = r"\b(?!tags\b)\w+[ \t]*(?:>=|<=|!=|=|>|<|:)"
+    return bool(re.search(pattern, text, re.IGNORECASE))
+
+
+def expression_contains_tags(text):
+    pattern = r"\btags\b[ \t]*(?:>=|<=|!=|=|>|<|:)"
+    return bool(re.search(pattern, text, re.IGNORECASE))
+
+
+class EvaluateExpression:
+    def __init__(self):
+        # Pre-define the grammar structure during initialization
+        self.grammar = self._build_grammar()
+
+    def _compare_single(self, l_val, op, r_val):
+        """
+        Atomic comparison logic for individual values.
+        Handles numeric conversion and standard operators.
+        """
+        # Numeric conversion for mathematical operators
+        if op in (">", "<", ">=", "<="):
+            try:
+                # Attempt to treat both sides as floats
+                curr_l, curr_r = float(l_val), float(r_val)
+            except (ValueError, TypeError):
+                # Fallback to string comparison if conversion fails
+                curr_l, curr_r = str(l_val), str(r_val)
+        else:
+            # Default to string representation for other operators
+            curr_l, curr_r = str(l_val), str(r_val)
+
+        # Standard operator logic
+        if op == "=":
+            return l_val == r_val
+        if op == "!=":
+            return l_val != r_val
+        if op == ">":
+            return curr_l > curr_r
+        if op == "<":
+            return curr_l < curr_r
+        if op == ">=":
+            return curr_l >= curr_r
+        if op == "<=":
+            return curr_l <= curr_r
+        if op == ":":
+            return str(r_val).lower() in str(l_val).lower()
+        return False
+
+    def _compare(self, data, left_key, op, right_val):
+        """
+        Main comparison router. Checks if the field is a list or a single value.
+        """
+        # Normalize data keys to lowercase for case-insensitive lookup
+        normalized_data = {k.lower(): v for k, v in data.items()}
+
+        # Extract the left-hand value (the field from the JSON)
+        l_val = normalized_data.get(left_key.lower(), left_key)
+
+        # Extract the right-hand value (check if it's a literal or another field)
+        r_val = normalized_data.get(str(right_val).lower(), right_val)
+
+        # IF THE FIELD VALUE IS A LIST
+        if isinstance(l_val, list):
+            # Return True if ANY item in the list satisfies the condition
+            return any(self._compare_single(item, op, r_val) for item in l_val)
+
+        # IF THE FIELD VALUE IS A SINGLE DATA POINT
+        return self._compare_single(l_val, op, r_val)
+
+    def _build_grammar(self):
+        """
+        Defines the pyparsing grammar for the expression engine.
+        """
+        operators = one_of(">= <= != = > < :")
+        identifier = Word(alphanums + "_./\\")
+        quoted_string = QuotedString("'") | QuotedString('"')
+        operand = quoted_string | identifier
+
+        # Define basic condition (e.g., "width > 100" or "word")
+        condition = Group((operand + operators + operand) | operand)
+
+        # Attach the parse action to convert tokens into executable functions (lambdas)
+        condition.set_parse_action(lambda t: self._create_evaluator_func(t[0]))
+
+        return infix_notation(
+            condition,
+            [
+                ("NOT", 1, opAssoc.RIGHT, lambda t: (
+                    lambda data: not t[0][1](data))),
+                ("AND", 2, opAssoc.LEFT, lambda t: (
+                    lambda data: all(f(data) for f in t[0] if callable(f)))),
+                ("OR", 2, opAssoc.LEFT, lambda t: (
+                    lambda data: any(f(data) for f in t[0] if callable(f)))),
+            ],
+        )
+
+    def _create_evaluator_func(self, tokens):
+        """
+        Creates a closure that captures tokens and waits for the data dictionary.
+        """
+        if len(tokens) == 1:
+            # Rule: Single term -> path CONTAINS term
+            return lambda data: self._compare(data, 'path', ':', tokens[0])
+        else:
+            # Rule: Explicit triplet (key, operator, value)
+            return lambda data: self._compare(data, tokens[0], tokens[1], tokens[2])
+
+    def compile(self, expression):
+        """
+        Parses the expression once and returns a reusable function.
+        """
+        try:
+            return self.grammar.parse_string(expression, parse_all=True)[0]
+        except Exception as e:
+            print(f"Compilation Error: {e}")
+            # Fallback: return a function that always fails gracefully
+            return lambda data: False
+
 
 class BagheeraSearcher:
     """Class to handle Baloo searches and interact with the C wrapper."""
@@ -69,84 +196,8 @@ class BagheeraSearcher:
 
         return lib
 
-    def check_keywords(
-        self, text: str, query: str, file_path: str = "", file_id: int = 0
-    ) -> bool:
-        """
-        Evaluates if a text meets a logical query.
-        Supports: AND, OR, ( ), dimensions (width=height, etc.), and shapes.
-        """
-        if file_path:
-            try:
-                w, h = get_resolution(file_id)
-            except Exception:
-                w, h = -1, -1
-
-            def replace_dim(match: re.Match) -> str:
-                if w <= 0 or h <= 0:
-                    return "__false__"
-
-                s = match.group(0).upper()
-                if "PORTRAIT" in s:
-                    return "__true__" if w < h else "__false__"
-                if "LANDSCAPE" in s:
-                    return "__true__" if w > h else "__false__"
-                if "SQUARE" in s:
-                    return "__true__" if w == h else "__false__"
-
-                op = match.group(1)
-                ops_map = {
-                    "=": w == h,
-                    ">": w > h,
-                    "<": w < h,
-                    ">=": w >= h,
-                    "<=": w <= h,
-                    "!=": w != h,
-                }
-                return "__true__" if ops_map.get(op, False) else "__false__"
-
-            query = re.sub(
-                r"\b(PORTRAIT|LANDSCAPE|SQUARE)\b",
-                replace_dim,
-                query,
-                flags=re.IGNORECASE,
-            )
-            query = re.sub(
-                r"\bwidth\s*(<=|>=|!=|<|>|=)\s*height\b",
-                replace_dim,
-                query,
-                flags=re.IGNORECASE,
-            )
-
-        text = text.lower()
-        query = re.sub(r"(?<=\w)\s+(?=\w)", " AND ", query)
-
-        tokens = re.findall(r"\(|\)|OR|AND|[^\s()]+", query)
-        regex_parts = []
-
-        for t in tokens:
-            if t in ("(", ")"):
-                regex_parts.append(t)
-            elif t == "OR":
-                regex_parts.append("|")
-            elif t == "AND":
-                continue
-            elif t == "__true__":
-                regex_parts.append("(?=.*)")
-            elif t == "__false__":
-                regex_parts.append("(?!)")
-            else:
-                regex_parts.append(rf"(?=.*{re.escape(t)})")
-
-        final_regex = "".join(regex_parts).lower()
-
-        try:
-            return bool(re.search(f"^{final_regex}.*", text, re.DOTALL))
-        except re.error:
-            return False
-
     def get_baloo_info(self, file_path: str) -> Dict[str, str]:
-        """Retrieves properties for a specific file from Baloo."""
+        """Extract properties for a specific file directly from file."""
         result = self.baloo_lib.get_file_properties(file_path.encode("utf-8"))
         if not result:
             return {}
@@ -181,6 +232,8 @@ class BagheeraSearcher:
         options: Dict[str, Any],
         search_opts: Dict[str, Any],
         files_count: int,
+        exclude_evaluator: Any,
+        exclude_sources: Dict[str, bool]
     ) -> Iterator[Dict[str, Any]]:
         """Executes a recursive search yielded item by item."""
         options["query"] = query_text
@@ -195,15 +248,20 @@ class BagheeraSearcher:
                 continue
 
             self.ids_processed.add(file_id)
-            rec_exclude = search_opts.get("recursive_exclude")
 
-            if not rec_exclude or not self.check_keywords(
+            if exclude_evaluator:
-                item["path"], rec_exclude, item["path"], file_id
+                file_info = {'path': item["path"]}
-            ):
+                if exclude_sources.get('properties'):
+                    file_info = file_info | get_info(file_id)
+                if exclude_sources.get('tags'):
+                    file_info = file_info | get_tags(file_id)
+            else:
+                file_info = None
+
+            if not file_info or not exclude_evaluator(file_info):
                 if files_count >= search_opts.get("offset", 0):
                     search_opts["limit"] -= 1
                     yield item
-
                 files_count += 1
 
     def search(
@@ -215,6 +273,30 @@ class BagheeraSearcher:
         """
         Main search generator. Yields file dictionaries.
         """
+        if search_opts['exclude']:
+            ee = EvaluateExpression()
+            exclude_evaluator = ee.compile(search_opts['exclude'])
+            exclude_sources = {}
+            if expression_contains_property(search_opts['exclude']):
+                exclude_sources['properties'] = True
+            if expression_contains_tags(search_opts['exclude']):
+                exclude_sources['tags'] = True
+        else:
+            exclude_evaluator = None
+            exclude_sources = {}
+
+        if search_opts['recursive_exclude']:
+            ee = EvaluateExpression()
+            recurse_exclude_evaluator = ee.compile(search_opts['recursive_exclude'])
+            recurse_exclude_sources = {}
+            if expression_contains_property(search_opts['recursive_exclude']):
+                recurse_exclude_sources['properties'] = True
+            if expression_contains_tags(search_opts['recursive_exclude']):
+                recurse_exclude_sources['tags'] = True
+        else:
+            recurse_exclude_evaluator = None
+            recurse_exclude_sources = {}
+
         main_options["query"] = parse_date(query_text)
         files = self._execute_query(main_options)
 
@@ -241,15 +323,22 @@ class BagheeraSearcher:
                 continue
 
             self.ids_processed.add(file_id)
-            exclude_pattern = search_opts.get("exclude")
 
-            if not exclude_pattern or not self.check_keywords(
+            if exclude_evaluator:
-                item["path"], exclude_pattern, item["path"], file_id
+                file_info = {'path': item["path"]}
-            ):
+                if exclude_sources.get('properties'):
+                    file_info = file_info | get_info(file_id)
+                if exclude_sources.get('tags'):
+                    file_info = file_info | get_tags(file_id)
+            else:
+                file_info = None
+
+            if not file_info or not exclude_evaluator(file_info):
                 if is_recursive:
                     main_options["directory"] = item["path"]
                     yield from self.search_recursive(
-                        query_text, main_options, search_opts, files_count
+                        query_text, main_options, search_opts, files_count,
+                        recurse_exclude_evaluator, recurse_exclude_sources
                     )
                 else:
                     yield item

bagheerasearch.py

@@ -5,7 +5,7 @@ Bagheera Search Tool - CLI Client
 """
 
 __appname__ = "BagheeraSearch"
-__version__ = "1.0"
+__version__ = "1.1"
 __author__ = "Ignacio Serantes"
 __email__ = "kde@aynoa.net"
 __license__ = "LGPL"
@@ -24,9 +24,9 @@ from bagheera_search_lib import BagheeraSearcher
 # --- CONFIGURATION ---
 PROG_NAME = "Bagheera Search Tool"
 PROG_ID = "bagheerasearch"
-PROG_VERSION = "1.0"
+PROG_VERSION = __version__
-PROG_BY = "Ignacio Serantes"
+PROG_BY = __author__
-PROG_DATE = "2026-03-19"
+PROG_DATE = "2026-05-09"
 
 CONFIG_DIR = Path.home() / ".config" / PROG_ID
 CONFIG_FILE = CONFIG_DIR / "config.json"
@@ -61,9 +61,9 @@ Baloo offers a rich syntax for searching through your files. Certain attributes
 
 For example 'type' can be used to filter for files based on their general type:
 
-  type:Audio or type:Document
+  type:Audio OR type:Document
 
-The following comparison operators are supported, but note that 'not equal' operator is not available.
+The following comparison operators are supported, but note that 'not equal' (!=) operator is not available.
   · :   - contains (only for text comparison)
   · =   - equal
   · >   - greater than
@@ -72,7 +72,6 @@ The following comparison operators are supported, but note that 'not equal' oper
   · <=  - less than or equal to
 
 Currently the following types are supported:
-
   · Archive
   · Folder
   · Audio
@@ -83,9 +82,77 @@ Currently the following types are supported:
     · Presentation
   · Text
 
-These expressions can be combined using AND or OR and additional parenthesis, but note that 'NOT' logical operator is not available.
+These expressions can be combined using logical operators 'AND' or 'OR' and additional parenthesis, but note that 'NOT' logical operator is not available.
+
+
+The full list of properties which can be searched is listed below. They are grouped by file types.
+
+All Files
+  · filename
+  · mimetype
+  · modified
+  · rating
+  · tags
+  · userComment
+
+Audio
+  · Album
+  · AlbumArtist
+  · Artist
+  · BitRate
+  · Channels
+  · Comment
+  · Composer
+  · Duration
+  · Genre
+  · Lyricist
+  · ReleaseYear
+  · SampleRate
+  · TrackNumber
+
+Documents
+  · Author
+  · Copyright
+  · CreationDate
+  · Generator
+  · Keywords
+  · Language
+  · LineCount
+  · PageCount
+  · Publisher
+  · Subject
+  · Title
+  · WordCount
+
+Media
+  · AspectRatio
+  · FrameRate
+  · Height
+  · ImageDateTime
+  · ImageMake
+  · ImageModel
+  · ImageOrientation
+  · Images
+  · PhotoApertureValue
+  · PhotoDateTimeOriginal
+  · PhotoExposureBiasValue
+  · PhotoExposureTime
+  · PhotoFlash
+  · PhotoFNumber
+  · PhotoFocalLength
+  · PhotoFocalLengthIn35mmFilm
+  · PhotoGpsAltitude
+  · PhotoGpsLatitude
+  · PhotoGpsLongitude
+  · PhotoISOSpeedRatings
+  · PhotoMeteringMode
+  · PhotoPixelXDimension
+  · PhotoPixelYDimension
+  · PhotoSaturation
+  · PhotoSharpness
+  · PhotoWhiteBalance
+  · Width
 
-[... omitted for brevity, but includes the full list of searchable properties as in your original script ...]
 
 {PROG_NAME} recognizes some natural language sentences in English, as long as they are capitalized, and transforms them into queries that can be interpreted by the search engine.
 
@@ -93,21 +160,18 @@ Supported natural language sentences and patterns for queries are:
   · MODIFIED TODAY
   · MODIFIED YESTERDAY
   · MODIFIED THIS [ DAY | WEEK | MONTH | YEAR ]
-  · LAST <NUMBER> [ DAYS | WEEKS | MONTHS | YEARS ]
+  · MODIFIED LAST <NUMBER> [ DAYS | WEEKS | MONTHS | YEARS ]
-  · <NUMBER> [ DAYS | WEEKS | MONTHS | YEARS ] AGO
+  · MODIFIED <NUMBER> [ DAYS | WEEKS | MONTHS | YEARS ] AGO
 
 <NUMBER> can be any number or a number text from ONE to TWENTY.
 
-Remarks: LAST DAY, if used, is interpreted as YESTERDAY.
 
-Supported expressions for --exclude and --recursive-exclude are:
+The --exclude and --recursive-exclude options allow you to filter files out of the results. The syntax for both options supports parentheses and logical operators (AND, OR, and NOT) to combine multiple patterns.
-  · width<CMP_OP>height  - only if file has width and height properties
+In addition to standard query comparison operators, the not equal (!=) operator is available for comparing properties against specific values. Furthermore, you can compare two properties directly; for example, 'width > height' is a valid expression.
-  · height<CMP_OP>width  - only if file has width and height properties
+Remarks:
-  · PORTRAIT             - only if file width is greater or equal to height
+  · All text comparison are case insensitive.
-  · LANDSCAPE            - only if file height is greater or equal to width
+  · Tags comparisons are performed against both individual full tag string (using the '/' character as a level separator) and each individual level. All individual level values are normalized to lowercase and stripped of accents or diacritics. For example, a file tagged as 'Opera,Person/María Callas,Singer' would match any of the following elements: ['Opera', 'Person/María Callas', 'Singer', 'callas', 'maria', 'opera', 'person', 'singer']."
-  · SQUARE               - only if file width equals to height
+  · Only text and numeric data are supported."""
-
-<CMP_OP> can be: != | >= | <= | = | > | <"""
     print(help_query)
 
 
@@ -146,7 +210,7 @@ def main():
 
     parser.add_argument("--day", type=int, help="day fixed filter, --month is required")
     parser.add_argument("--month", type=int, help="month fixed filter, --year is required")
-    parser.add_argument("--year", type=int, help="year filter fixed filter")
+    parser.add_argument("--year", type=int, help="year fixed filter")
 
     parser.add_argument("--help-query", action="store_true", help="show query syntax help")
     parser.add_argument("--version", action="store_true", help="show version information")
@@ -163,7 +227,7 @@ def main():
         raise ValueError("Missing --month (required when --day is used)")
 
     if args.month is not None and args.year is None:
-        raise ValueError("Missing --year (requered when --month is used)")
+        raise ValueError("Missing --year (required when --month is used)")
 
     if args.help_query:
         print_help_query()

baloo_tools/__init__.py

@@ -1,7 +1,19 @@
 from .baloo_tools import BalooTools
 
 
+def get_info(id):
+    """Interfaz simplificada para la librería."""
+    tools = BalooTools()
+    return tools.get_info(id)
+
+
 def get_resolution(id):
     """Interfaz simplificada para la librería."""
     tools = BalooTools()
     return tools.get_resolution(id)
+
+
+def get_tags(id):
+    """Interfaz simplificada para la librería."""
+    tools = BalooTools()
+    return tools.get_tags(id)

baloo_tools/baloo_tools.py

@@ -8,9 +8,97 @@ Helper functions to interact directly with the Baloo LMDB index.
 import json
 import lmdb
 import os
+import re
 import sys
 from typing import Tuple
 
+PROPERTIES_ID_MAP = {
+    '0': 'Empty',
+    '1': 'BitRate',
+    '2': 'Channels',
+    '3': 'Duration',
+    '4': 'Genre',
+    '5': 'SampleRate',
+    '6': 'TrackNumber',
+    '7': 'ReleaseYear',
+    '8': 'Comment',
+    '9': 'Artist',
+    '10': 'Album',
+    '11': 'AlbumArtist',
+    '12': 'Composer',
+    '13': 'Lyricist',
+    '14': 'Author',
+    '15': 'Title',
+    '16': 'Subject',
+    '17': 'Generator',
+    '18': 'PageCount',
+    '19': 'WordCount',
+    '20': 'LineCount',
+    '21': 'Language',
+    '22': 'Copyright',
+    '23': 'Publisher',
+    '24': 'CreationDate',
+    '25': 'Keywords',
+    '26': 'Width',
+    '27': 'Height',
+    '28': 'AspectRatio',
+    '29': 'FrameRate',
+    '30': 'Manufacturer',
+    '31': 'Model',
+    '32': 'ImageDateTime',
+    '33': 'ImageOrientation',
+    '34': 'PhotoFlash',
+    '35': 'PhotoPixelXDimension',
+    '36': 'PhotoPixelYDimension',
+    '37': 'PhotoDateTimeOriginal',
+    '38': 'PhotoFocalLength',
+    '39': 'PhotoFocalLengthIn35mmFilm',
+    '40': 'PhotoExposureTime',
+    '41': 'PhotoFNumber',
+    '42': 'PhotoApertureValue',
+    '43': 'PhotoExposureBiasValue',
+    '44': 'PhotoWhiteBalance',
+    '45': 'PhotoMeteringMode',
+    '46': 'PhotoISOSpeedRatings',
+    '47': 'PhotoSaturation',
+    '48': 'PhotoSharpness',
+    '49': 'PhotoGpsLatitude',
+    '50': 'PhotoGpsLongitude',
+    '51': 'PhotoGpsAltitude',
+    '52': 'TranslationUnitsTotal',
+    '53': 'TranslationUnitsWithTranslation',
+    '54': 'TranslationUnitsWithDraftTranslation',
+    '55': 'TranslationLastAuthor',
+    '56': 'TranslationLastUpDate',
+    '57': 'TranslationTemplateDate',
+    '58': 'OriginUrl',
+    '59': 'OriginEmailSubject',
+    '60': 'OriginEmailSender',
+    '61': 'OriginEmailMessageId',
+    '62': 'DiscNumber',
+    '63': 'Location',
+    '64': 'Performer',
+    '65': 'Ensemble',
+    '66': 'Arranger',
+    '67': 'Conductor',
+    '68': 'Opus',
+    '69': 'Label',
+    '70': 'Compilation',
+    '71': 'License',
+    '72': 'Rating',
+    '73': 'Lyrics',
+    '74': 'ReplayGainAlbumPeak',
+    '75': 'ReplayGainAlbumGain',
+    '76': 'ReplayGainTrackPeak',
+    '77': 'ReplayGainTrackGain',
+    '78': 'Description',
+    '79': 'VideoCodec',
+    '80': 'AudioCodec',
+    '81': 'PixelFormat',
+    '82': 'ColorSpace',
+    '83': 'AssistiveAlternateDescription'
+}
+
 
 class BalooTools:
     """Class to interact directly with the Baloo LMDB index."""
@@ -21,16 +109,15 @@ class BalooTools:
             os.path.expanduser("~"), ".local/share/baloo/index"
         )
 
-    def get_resolution(self, file_id: int, sep: str = 'x') -> Tuple[int, int]:
+    def get_info(self, file_id: int) -> json:
         """
-        Retrieves the width and height of an image/video from the Baloo index.
+        Retrieves file metadata from the Baloo index.
 
         Args:
             file_id: The integer ID of the file.
-            sep: Separator used (unused currently, kept for compatibility).
 
         Returns:
-            A tuple of (width, height) integers. Returns (-1, -1) if not found.
+            A json with all file metadata fields.
         """
         try:
             # Using context manager ensures the environment is closed properly
@@ -58,16 +145,86 @@ class BalooTools:
 
                             try:
                                 jvalue = json.loads(value.decode())
-                                # Baloo stores width in '26' and height in '27'
+                                return {PROPERTIES_ID_MAP.get(k, k):
-                                return jvalue.get('26', -1), jvalue.get('27', -1)
+                                        v for k, v in jvalue.items()}
                             except (json.JSONDecodeError, KeyError):
-                                return -1, -1
+                                return {}
 
         except lmdb.Error as e:
             print(f"Warning: Failed to access Baloo LMDB index: {e}", file=sys.stderr)
 
+        return {}
+
+    def get_resolution(self, file_id: int, sep: str = 'x') -> Tuple[int, int]:
+        """
+        Retrieves the width and height of an image/video from the Baloo index.
+
+        Args:
+            file_id: The integer ID of the file.
+            sep: Separator used (unused currently, kept for compatibility).
+
+        Returns:
+            A tuple of (width, height) integers. Returns (-1, -1) if not found.
+        """
+        file_info = self.get_info(file_id)
+        try:
+            return file_info.get('26', -1), file_info.get('27', -1)
+        except (json.JSONDecodeError, KeyError):
             return -1, -1
 
+    def get_tags(self, file_id: int) -> json:
+        """
+        Retrieves a string with all file tags from the Baloo index.
+
+        Args:
+            file_id: The integer ID of the file.
+
+        Returns:
+            A json with a field called tags with all tags comma separated.
+        """
+        try:
+            # Using context manager ensures the environment is closed properly
+            with lmdb.Environment(
+                self.baloo_db_path,
+                subdir=False,
+                readonly=True,
+                lock=False,
+                max_dbs=20
+            ) as env:
+                document_data_db = env.open_db(b'docxatrrterms')
+
+                with env.begin() as txn:
+                    cursor = txn.cursor(document_data_db)
+
+                    # Convert ID to 8-byte little-endian format
+                    file_id_bytes = int.to_bytes(
+                        file_id, length=8, byteorder='little', signed=False
+                    )
+
+                    if cursor.set_range(file_id_bytes):
+                        for key, value in cursor:
+                            if key != file_id_bytes:
+                                break
+
+                            text = value.decode('utf-8', errors='replace')
+                            text = re.sub(r'\x00(?![T])', '', text)
+                            parts = re.split(r'[\x00\x01]', text)
+
+                            tags = []
+                            for p in parts:
+                                p = p.strip()
+                                if p:
+                                    tag = p.removeprefix('TAG-').removeprefix('TA')
+                                    tags.append(tag)
+
+                            return {'tags': tags}
+                            # return {'tags': ",".join(tags)}
+
+        except lmdb.Error as e:
+            print(f"Warning: Failed to access Baloo LMDB index: {e}", file=sys.stderr)
+
+        return {}
+
 
 # Helper function to maintain compatibility with bagheera_search_lib.py
 # since it imports `get_resolution` directly.

pyproject.toml

@@ -0,0 +1,39 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "bagheerasearch"
+version = "1.1.0"
+authors = [
+  { name="Ignacio Serantes" },
+]
+description = "Bagheera Search Tool"
+readme = "README.md"
+requires-python = ">=3.8"
+dependencies = [
+    "lmdb",
+    "pyparsing",
+]
+
+[project.scripts]
+bagheerasearch = "bagheerasearch:main"
+
+[tool.setuptools]
+py-modules = ["bagheerasearch"]
+packages = [
+    "bagheera_query_parser_lib",
+    "bagheera_search_lib",
+    "baloo_tools"
+]
+include-package-data = true
+zip-safe = false
+
+[tool.setuptools.package-dir]
+"" = "."
+"bagheera_query_parser_lib" = "bagheera_query_parser_lib"
+"bagheera_search_lib" = "bagheera_search_lib"
+"baloo_tools" = "baloo_tools"
+
+[tool.setuptools.package-data]
+"*" = ["libbaloo_wrapper.so"]

setup.py

@@ -6,12 +6,7 @@ from setuptools.command.install import install
 from setuptools.command.develop import develop
 from setuptools.command.build_ext import build_ext
 
-
 def compile_wrapper():
-    """
-    Compila libbaloo_wrapper.so forzando la ruta de inclusión profunda
-    detectada para KFileMetaData en KF6.
-    """
     base_path = os.path.abspath(os.path.dirname(__file__))
     source_file = os.path.join(base_path, 'baloo_wrapper', 'baloo_wrapper.cpp')
     output_lib = os.path.join(base_path, 'libbaloo_wrapper.so')
@@ -20,37 +15,22 @@ def compile_wrapper():
         print(f"✘ Error: Source file not found at {source_file}")
         sys.exit(1)
 
-    # Paquetes para pkg-config (nombres comunes en KF6)
+    packages = ['KF6Baloo', 'KF6BalooEngine', 'KF6FileMetadata', 'KF6CoreAddons', 'Qt6Core']
-    packages = [
-        'KF6Baloo',
-        'KF6BalooEngine',
-        'KF6FileMetadata',
-        'KF6CoreAddons',
-        'Qt6Core'
-    ]
-
     cflags = []
     libs = []
 
-    print("Detecting KF6 dependencies...")
     for pkg in packages:
         try:
-            cf = subprocess.check_output(['pkg-config', '--cflags', pkg],
+            cf = subprocess.check_output(['pkg-config', '--cflags', pkg], text=True).split()
-                                         text=True).split()
+            lb = subprocess.check_output(['pkg-config', '--libs', pkg], text=True).split()
-            lb = subprocess.check_output(['pkg-config', '--libs', pkg],
-                                         text=True).split()
             cflags.extend(cf)
             libs.extend(lb)
-            print(f"  [OK] {pkg}")
         except subprocess.CalledProcessError:
             print(f"  [!] Warning: pkg-config could not find {pkg}")
 
-    # CONFIGURACIÓN DE RUTAS SEGÚN TU SISTEMA:
-    # Añadimos el nivel intermedio para que <KFileMetaData/ExtractorCollection>
-    # se encuentre en /usr/include/KF6/KFileMetaData/KFileMetaData/
     extra_includes = [
         '-I/usr/include/KF6',
-        '-I/usr/include/KF6/KFileMetaData',  # Permite resolver KFileMetaData/
+        '-I/usr/include/KF6/KFileMetaData',
         '-I/usr/include/qt6',
         '-I/usr/include/qt6/QtCore'
     ]
@@ -58,7 +38,6 @@ def compile_wrapper():
     cflags = list(set(cflags + extra_includes))
     libs = list(set(libs))
 
-    # Comando de compilación C++17 replicando tu CMakeLists.txt [cite: 1, 2]
     compile_cmd = [
         'g++', '-shared', '-o', output_lib,
         '-fPIC', '-std=c++17',
@@ -68,60 +47,158 @@ def compile_wrapper():
     try:
         print(f"Executing compilation:\n{' '.join(compile_cmd)}")
         subprocess.check_call(compile_cmd)
-
-        if os.path.exists(output_lib):
-            print(f"✔ Successfully compiled: {output_lib}")
-        else:
-            raise FileNotFoundError("Compilation finished but .so file is missing.")
-
     except subprocess.CalledProcessError as e:
-        print(f"\n✘ Compilation failed (Exit code {e.returncode}).")
+        print(f"\n✘ Compilation failed.")
         sys.exit(1)
 
-
 class CustomInstall(install):
     def run(self):
         compile_wrapper()
         super().run()
 
-
 class CustomDevelop(develop):
     def run(self):
         compile_wrapper()
         super().run()
 
-
 class CustomBuildExt(build_ext):
     def run(self):
         compile_wrapper()
         super().run()
 
-
+# Solo dejamos cmdclass, el resto se lee de pyproject.toml
 setup(
-    name="bagheerasearch",
-    version="1.0.0",
-    author="Ignacio Serantes",
-    description="Bagheera Search Tool & Lib (KF6/C++17)",
-    py_modules=["bagheerasearch"],
-    package_dir={
-        "": ".",
-        "bagheera_query_parser_lib": "bagheera_query_parser_lib",
-        "bagheera_search_lib": "bagheera_search_lib",
-        "baloo_tools": "baloo_tools",
-    },
-    packages=[
-        "bagheera_query_parser_lib",
-        "bagheera_search_lib",
-        "baloo_tools"
-    ],
-    install_requires=["lmdb"],
-    entry_points={'console_scripts': ['bagheerasearch=bagheerasearch:main']},
     cmdclass={
         'install': CustomInstall,
         'develop': CustomDevelop,
         'build_ext': CustomBuildExt,
-    },
+    }
-    data_files=[('lib', ['libbaloo_wrapper.so'])],
-    include_package_data=True,
-    zip_safe=False,
 )
+
+# import os
+# import subprocess
+# import sys
+# from setuptools import setup
+# from setuptools.command.install import install
+# from setuptools.command.develop import develop
+# from setuptools.command.build_ext import build_ext
+#
+#
+# def compile_wrapper():
+#     """
+#     Compila libbaloo_wrapper.so forzando la ruta de inclusión profunda
+#     detectada para KFileMetaData en KF6.
+#     """
+#     base_path = os.path.abspath(os.path.dirname(__file__))
+#     source_file = os.path.join(base_path, 'baloo_wrapper', 'baloo_wrapper.cpp')
+#     output_lib = os.path.join(base_path, 'libbaloo_wrapper.so')
+#
+#     if not os.path.exists(source_file):
+#         print(f"✘ Error: Source file not found at {source_file}")
+#         sys.exit(1)
+#
+#     # Paquetes para pkg-config (nombres comunes en KF6)
+#     packages = [
+#         'KF6Baloo',
+#         'KF6BalooEngine',
+#         'KF6FileMetadata',
+#         'KF6CoreAddons',
+#         'Qt6Core'
+#     ]
+#
+#     cflags = []
+#     libs = []
+#
+#     print("Detecting KF6 dependencies...")
+#     for pkg in packages:
+#         try:
+#             cf = subprocess.check_output(['pkg-config', '--cflags', pkg],
+#                                          text=True).split()
+#             lb = subprocess.check_output(['pkg-config', '--libs', pkg],
+#                                          text=True).split()
+#             cflags.extend(cf)
+#             libs.extend(lb)
+#             print(f"  [OK] {pkg}")
+#         except subprocess.CalledProcessError:
+#             print(f"  [!] Warning: pkg-config could not find {pkg}")
+#
+#     # CONFIGURACIÓN DE RUTAS SEGÚN TU SISTEMA:
+#     # Añadimos el nivel intermedio para que <KFileMetaData/ExtractorCollection>
+#     # se encuentre en /usr/include/KF6/KFileMetaData/KFileMetaData/
+#     extra_includes = [
+#         '-I/usr/include/KF6',
+#         '-I/usr/include/KF6/KFileMetaData',  # Permite resolver KFileMetaData/
+#         '-I/usr/include/qt6',
+#         '-I/usr/include/qt6/QtCore'
+#     ]
+#
+#     cflags = list(set(cflags + extra_includes))
+#     libs = list(set(libs))
+#
+#     # Comando de compilación C++17 replicando tu CMakeLists.txt [cite: 1, 2]
+#     compile_cmd = [
+#         'g++', '-shared', '-o', output_lib,
+#         '-fPIC', '-std=c++17',
+#         source_file
+#     ] + cflags + libs
+#
+#     try:
+#         print(f"Executing compilation:\n{' '.join(compile_cmd)}")
+#         subprocess.check_call(compile_cmd)
+#
+#         if os.path.exists(output_lib):
+#             print(f"✔ Successfully compiled: {output_lib}")
+#         else:
+#             raise FileNotFoundError("Compilation finished but .so file is missing.")
+#
+#     except subprocess.CalledProcessError as e:
+#         print(f"\n✘ Compilation failed (Exit code {e.returncode}).")
+#         sys.exit(1)
+#
+#
+# class CustomInstall(install):
+#     def run(self):
+#         compile_wrapper()
+#         super().run()
+#
+#
+# class CustomDevelop(develop):
+#     def run(self):
+#         compile_wrapper()
+#         super().run()
+#
+#
+# class CustomBuildExt(build_ext):
+#     def run(self):
+#         compile_wrapper()
+#         super().run()
+#
+#
+# setup(
+#     name="bagheerasearch",
+#     version="1.0.0",
+#     author="Ignacio Serantes",
+#     description="Bagheera Search Tool & Lib (KF6/C++17)",
+#     py_modules=["bagheerasearch"],
+#     package_dir={
+#         "": ".",
+#         "bagheera_query_parser_lib": "bagheera_query_parser_lib",
+#         "bagheera_search_lib": "bagheera_search_lib",
+#         "baloo_tools": "baloo_tools",
+#     },
+#     packages=[
+#         "bagheera_query_parser_lib",
+#         "bagheera_search_lib",
+#         "baloo_tools"
+#     ],
+#     install_requires=["lmdb"],
+#     entry_points={'console_scripts': ['bagheerasearch=bagheerasearch:main']},
+#     cmdclass={
+#         'install': CustomInstall,
+#         'develop': CustomDevelop,
+#         'build_ext': CustomBuildExt,
+#     },
+#     data_files=[('lib', ['libbaloo_wrapper.so'])],
+#     include_package_data=True,
+#     zip_safe=False,
+# )