@piecemaker-legal/piecemaker 1.0.0

package/server/piecemaker/vendor/websocket-server/scripts/presidio_analyzer/predefined_recognizers/generic/email_recognizer.py

@@ -0,0 +1,48 @@
+from typing import List, Optional
+
+import tldextract
+
+from presidio_analyzer import Pattern, PatternRecognizer
+
+
+class EmailRecognizer(PatternRecognizer):
+    """
+    Recognize email addresses using regex.
+
+    :param patterns: List of patterns to be used by this recognizer
+    :param context: List of context words to increase confidence in detection
+    :param supported_language: Language this recognizer supports
+    :param supported_entity: The entity this recognizer can detect
+    """
+
+    PATTERNS = [
+        Pattern(
+            "Email (Medium)",
+            r"\b((([!#$%&'*+\-/=?^_`{|}~\w])|([!#$%&'*+\-/=?^_`{|}~\w][!#$%&'*+\-/=?^_`{|}~\.\w]{0,}[!#$%&'*+\-/=?^_`{|}~\w]))[@]\w+([-.]\w+)*\.\w+([-.]\w+)*)\b",
+            0.5,
+        ),
+    ]
+
+    CONTEXT = ["email"]
+
+    def __init__(
+        self,
+        patterns: Optional[List[Pattern]] = None,
+        context: Optional[List[str]] = None,
+        supported_language: str = "en",
+        supported_entity: str = "EMAIL_ADDRESS",
+        name: Optional[str] = None,
+    ):
+        patterns = patterns if patterns else self.PATTERNS
+        context = context if context else self.CONTEXT
+        super().__init__(
+            supported_entity=supported_entity,
+            patterns=patterns,
+            context=context,
+            supported_language=supported_language,
+            name=name,
+        )
+
+    def validate_result(self, pattern_text: str):  # noqa: D102
+        result = tldextract.extract(pattern_text)
+        return result.fqdn != ""

package/server/piecemaker/vendor/websocket-server/scripts/presidio_analyzer/predefined_recognizers/generic/iban_patterns.py

@@ -0,0 +1,173 @@
+"""
+List of different regex patterns for IBAN.
+
+The IBAN patterns are based on the IBAN specification here
+https://en.wikipedia.org/wiki/International_Bank_Account_Number
+In addition, an IBAN example per country can be found here:
+git shttps://www.xe.com/ibancalculator/countrylist
+An IBAN checker is available here: https://www.iban.com/iban-checker
+"""
+
+# IBAN parts format
+CC = "[A-Z]{2}"  # country code
+CK = "[0-9]{2}[ ]?"  # checksum
+BOS = "^"
+EOS = "$"  # end of string
+
+A = "[A-Z][ ]?"
+A2 = "([A-Z][ ]?){2}"
+A3 = "([A-Z][ ]?){3}"
+A4 = "([A-Z][ ]?){4}"
+
+C = "[a-zA-Z0-9][ ]?"
+C2 = "([a-zA-Z0-9][ ]?){2}"
+C3 = "([a-zA-Z0-9][ ]?){3}"
+C4 = "([a-zA-Z0-9][ ]?){4}"
+
+N = "[0-9][ ]?"
+N2 = "([0-9][ ]?){2}"
+N3 = "([0-9][ ]?){3}"
+N4 = "([0-9][ ]?){4}"
+
+regex_per_country = {
+    # Albania (8n, 16c) ALkk bbbs sssx cccc cccc cccc cccc
+    "AL": "(AL)" + CK + N4 + N4 + C4 + C4 + C4 + C4,
+    # Andorra (8n, 12c) ADkk bbbb ssss cccc cccc cccc
+    "AD": "(AD)" + CK + N4 + N4 + C4 + C4 + C4,
+    # Austria (16n) ATkk bbbb bccc cccc cccc
+    "AT": "(AT)" + CK + N4 + N4 + N4 + N4,
+    # Azerbaijan    (4c,20n) AZkk bbbb cccc cccc cccc cccc cccc
+    "AZ": "(AZ)" + CK + C4 + N4 + N4 + N4 + N4 + N4,
+    # Bahrain   (4a,14c)    BHkk bbbb cccc cccc cccc cc
+    "BH": "(BH)" + CK + A4 + C4 + C4 + C4 + C2,
+    # Belarus (4c, 4n, 16c)   BYkk bbbb aaaa cccc cccc cccc cccc
+    "BY": "(BY)" + CK + C4 + N4 + C4 + C4 + C4 + C4,
+    # Belgium (12n)   BEkk bbbc cccc ccxx
+    "BE": "(BE)" + CK + N4 + N4 + N4,
+    # Bosnia and Herzegovina    (16n)   BAkk bbbs sscc cccc ccxx
+    "BA": "(BA)" + CK + N4 + N4 + N4 + N4,
+    # Brazil (23n,1a,1c) BRkk bbbb bbbb ssss sccc cccc ccct n
+    "BR": "(BR)" + CK + N4 + N4 + N4 + N4 + N4 + N3 + A + C,
+    # Bulgaria  (4a,6n,8c)  BGkk bbbb ssss ttcc cccc cc
+    "BG": "(BG)" + CK + A4 + N4 + N + N + C2 + C4 + C2,
+    # Costa Rica    (18n)   CRkk 0bbb cccc cccc cccc cc (0 = always zero)
+    "CR": "(CR)" + CK + "[0]" + N3 + N4 + N4 + N4 + N2,
+    # Croatia   (17n)   HRkk bbbb bbbc cccc cccc c
+    "HR": "(HR)" + CK + N4 + N4 + N4 + N4 + N,
+    # Cyprus    (8n,16c)    CYkk bbbs ssss cccc cccc cccc cccc
+    "CY": "(CY)" + CK + N4 + N4 + C4 + C4 + C4 + C4,
+    # Czech Republic    (20n)   CZkk bbbb ssss sscc cccc cccc
+    "CZ": "(CZ)" + CK + N4 + N4 + N4 + N4 + N4,
+    # Denmark   (14n)   DKkk bbbb cccc cccc cc
+    "DK": "(DK)" + CK + N4 + N4 + N4 + N2,
+    # Dominican Republic    (4a,20n)    DOkk bbbb cccc cccc cccc cccc cccc
+    "DO": "(DO)" + CK + A4 + N4 + N4 + N4 + N4 + N4,
+    # EAt Timor    (19n) TLkk bbbc cccc cccc cccc cxx
+    "TL": "(TL)" + CK + N4 + N4 + N4 + N4 + N3,
+    # Estonia   (16n) EEkk bbss cccc cccc cccx
+    "EE": "(EE)" + CK + N4 + N4 + N4 + N4,
+    # Faroe Islands    (14n) FOkk bbbb cccc cccc cx
+    "FO": "(FO)" + CK + N4 + N4 + N4 + N2,
+    # Finland   (14n) FIkk bbbb bbcc cccc cx
+    "FI": "(FI)" + CK + N4 + N4 + N4 + N2,
+    # France    (10n,11c,2n) FRkk bbbb bsss sscc cccc cccc cxx
+    "FR": "(FR)" + CK + N4 + N4 + N2 + C2 + C4 + C4 + C + N2,
+    # Georgia   (2c,16n)  GEkk bbcc cccc cccc cccc cc
+    "GE": "(GE)" + CK + C2 + N2 + N4 + N4 + N4 + N2,
+    # Germany   (18n) DEkk bbbb bbbb cccc cccc cc
+    "DE": "(DE)" + CK + N4 + N4 + N4 + N4 + N2,
+    # Gibraltar (4a,15c)  GIkk bbbb cccc cccc cccc ccc
+    "GI": "(GI)" + CK + A4 + C4 + C4 + C4 + C3,
+    # Greece    (7n,16c)  GRkk bbbs sssc cccc cccc cccc ccc
+    "GR": "(GR)" + CK + N4 + N3 + C + C4 + C4 + C4 + C3,
+    # Greenland     (14n) GLkk bbbb cccc cccc cc
+    "GL": "(GL)" + CK + N4 + N4 + N4 + N2,
+    # Guatemala (4c,20c)  GTkk bbbb mmtt cccc cccc cccc cccc
+    "GT": "(GT)" + CK + C4 + C4 + C4 + C4 + C4 + C4,
+    # Hungary   (24n) HUkk bbbs sssx cccc cccc cccc cccx
+    "HU": "(HU)" + CK + N4 + N4 + N4 + N4 + N4 + N4,
+    # Iceland   (22n) ISkk bbbb sscc cccc iiii iiii ii
+    "IS": "(IS)" + CK + N4 + N4 + N4 + N4 + N4 + N2,
+    # Ireland   (4c,14n)  IEkk aaaa bbbb bbcc cccc cc
+    "IE": "(IE)" + CK + C4 + N4 + N4 + N4 + N2,
+    # Israel (19n) ILkk bbbn nncc cccc cccc ccc
+    "IL": "(IL)" + CK + N4 + N4 + N4 + N4 + N3,
+    # Italy (1a,10n,12c)  ITkk xbbb bbss sssc cccc cccc ccc
+    "IT": "(IT)" + CK + A + N3 + N4 + N3 + C + C3 + C + C4 + C3,
+    # Jordan    (4a,22n)  JOkk bbbb ssss cccc cccc cccc cccc cc
+    "JO": "(JO)" + CK + A4 + N4 + N4 + N4 + N4 + N4 + N2,
+    # Kazakhstan    (3n,13c)  KZkk bbbc cccc cccc cccc
+    "KZ": "(KZ)" + CK + N3 + C + C4 + C4 + C4,
+    # Kosovo    (4n,10n,2n)   XKkk bbbb cccc cccc cccc
+    "XK": "(XK)" + CK + N4 + N4 + N4 + N4,
+    # Kuwait    (4a,22c)  KWkk bbbb cccc cccc cccc cccc cccc cc
+    "KW": "(KW)" + CK + A4 + C4 + C4 + C4 + C4 + C4 + C2,
+    # Latvia    (4a,13c)  LVkk bbbb cccc cccc cccc c
+    "LV": "(LV)" + CK + A4 + C4 + C4 + C4 + C,
+    # Lebanon   (4n,20c)  LBkk bbbb cccc cccc cccc cccc cccc
+    "LB": "(LB)" + CK + N4 + C4 + C4 + C4 + C4 + C4,
+    # LiechteNtein (5n,12c)  LIkk bbbb bccc cccc cccc c
+    "LI": "(LI)" + CK + N4 + N + C3 + C4 + C4 + C,
+    # Lithuania (16n) LTkk bbbb bccc cccc cccc
+    "LT": "(LT)" + CK + N4 + N4 + N4 + N4,
+    # Luxembourg    (3n,13c)  LUkk bbbc cccc cccc cccc
+    "LU": "(LU)" + CK + N3 + C + C4 + C4 + C4,
+    # Malta (4a,5n,18c)   MTkk bbbb ssss sccc cccc cccc cccc ccc
+    "MT": "(MT)" + CK + A4 + N4 + N + C3 + C4 + C4 + C4 + C3,
+    # Mauritania    (23n) MRkk bbbb bsss sscc cccc cccc cxx
+    "MR": "(MR)" + CK + N4 + N4 + N4 + N4 + N4 + N3,
+    # Mauritius (4a,19n,3a)   MUkk bbbb bbss cccc cccc cccc 000m mm
+    "MU": "(MU)" + CK + A4 + N4 + N4 + N4 + N4 + N3 + A,
+    # Moldova   (2c,18c)  MDkk bbcc cccc cccc cccc cccc
+    "MD": "(MD)" + CK + C4 + C4 + C4 + C4 + C4,
+    # Monaco    (10n,11c,2n)  MCkk bbbb bsss sscc cccc cccc cxx
+    "MC": "(MC)" + CK + N4 + N4 + N2 + C2 + C4 + C4 + C + N2,
+    # Montenegro    (18n) MEkk bbbc cccc cccc cccc xx
+    "ME": "(ME)" + CK + N4 + N4 + N4 + N4 + N2,
+    # Netherlands   (4a,10n)  NLkk bbbb cccc cccc cc
+    "NL": "(NL)" + CK + A4 + N4 + N4 + N2,
+    # North Macedonia   (3n,10c,2n)   MKkk bbbc cccc cccc cxx
+    "MK": "(MK)" + CK + N3 + C + C4 + C4 + C + N2,
+    # Norway    (11n) NOkk bbbb cccc ccx
+    "NO": "(NO)" + CK + N4 + N4 + N3,
+    # Pakistan  (4c,16n)  PKkk bbbb cccc cccc cccc cccc
+    "PK": "(PK)" + CK + C4 + N4 + N4 + N4 + N4,
+    # Palestinian territories   (4c,21n)  PSkk bbbb xxxx xxxx xccc cccc cccc c
+    "PS": "(PS)" + CK + C4 + N4 + N4 + N4 + N4 + N,
+    # Poland    (24n) PLkk bbbs sssx cccc cccc cccc cccc
+    "PL": "(PL)" + CK + N4 + N4 + N4 + N4 + N4 + N4,
+    # Portugal  (21n) PTkk bbbb ssss cccc cccc cccx x
+    "PT": "(PT)" + CK + N4 + N4 + N4 + N4 + N,
+    # Qatar (4a,21c)  QAkk bbbb cccc cccc cccc cccc cccc c
+    "QA": "(QA)" + CK + A4 + C4 + C4 + C4 + C4 + C,
+    # Romania   (4a,16c)  ROkk bbbb cccc cccc cccc cccc
+    "RO": "(RO)" + CK + A4 + C4 + C4 + C4 + C4,
+    # San Marino    (1a,10n,12c)  SMkk xbbb bbss sssc cccc cccc ccc
+    "SM": "(SM)" + CK + A + N3 + N4 + N3 + C + C4 + C4 + C3,
+    # Saudi Arabia  (2n,18c)  SAkk bbcc cccc cccc cccc cccc
+    "SA": "(SA)" + CK + N2 + C2 + C4 + C4 + C4 + C4,
+    # Serbia    (18n) RSkk bbbc cccc cccc cccc xx
+    "RS": "(RS)" + CK + N4 + N4 + N4 + N4 + N2,
+    # Slovakia  (20n) SKkk bbbb ssss sscc cccc cccc
+    "SK": "(SK)" + CK + N4 + N4 + N4 + N4 + N4,
+    # Slovenia  (15n) SIkk bbss sccc cccc cxx
+    "SI": "(SI)" + CK + N4 + N4 + N4 + N3,
+    # Spain (20n) ESkk bbbb ssss xxcc cccc cccc
+    "ES": "(ES)" + CK + N4 + N4 + N4 + N4 + N4,
+    # Sweden    (20n) SEkk bbbc cccc cccc cccc cccc
+    "SE": "(SE)" + CK + N4 + N4 + N4 + N4 + N4,
+    # Switzerland   (5n,12c)  CHkk bbbb bccc cccc cccc c
+    "CH": "(CH)" + CK + N4 + N + C3 + C4 + C4 + C,
+    # Tunisia   (20n) TNkk bbss sccc cccc cccc cccc
+    "TN": "(TN)" + CK + N4 + N4 + N4 + N4 + N4,
+    # Turkey    (5n,17c)  TRkk bbbb bxcc cccc cccc cccc cc
+    "TR": "(TR)" + CK + N4 + N + C3 + C4 + C4 + C4 + C2,
+    # United Arab Emirates  (3n,16n)  AEkk bbbc cccc cccc cccc ccc
+    "AE": "(AE)" + CK + N4 + N4 + N4 + N4 + N3,
+    # United Kingdom (4a,14n) GBkk bbbb ssss sscc cccc cc
+    "GB": "(GB)" + CK + A4 + N4 + N4 + N4 + N2,
+    # Vatican City  (3n,15n)  VAkk bbbc cccc cccc cccc cc
+    "VA": "(VA)" + CK + N4 + N4 + N4 + N4 + N2,
+    # Virgin Islands, British   (4c,16n)  VGkk bbbb cccc cccc cccc cccc
+    "VG": "(VG)" + CK + C4 + N4 + N4 + N4 + N4,
+}

package/server/piecemaker/vendor/websocket-server/scripts/presidio_analyzer/predefined_recognizers/generic/iban_recognizer.py

@@ -0,0 +1,221 @@
+import logging
+import string
+from typing import Dict, List, Optional, Tuple
+
+import regex as re
+
+from presidio_analyzer import (
+    EntityRecognizer,
+    Pattern,
+    PatternRecognizer,
+    RecognizerResult,
+)
+from presidio_analyzer.nlp_engine import NlpArtifacts
+from presidio_analyzer.predefined_recognizers.generic.iban_patterns import (
+    BOS,
+    EOS,
+    regex_per_country,
+)
+
+logger = logging.getLogger("presidio-analyzer")
+
+
+class IbanRecognizer(PatternRecognizer):
+    """
+    Recognize IBAN code using regex and checksum.
+
+    :param patterns: List of patterns to be used by this recognizer
+    :param context: List of context words to increase confidence in detection
+    :param supported_language: Language this recognizer supports
+    :param supported_entity: The entity this recognizer can detect
+    :param exact_match: Whether patterns should be exactly matched or not
+    :param bos_eos: Tuple of strings for beginning of string (BOS)
+    and end of string (EOS)
+    :param regex_flags: Regex flags options
+    :param replacement_pairs: List of tuples with potential replacement values
+    for different strings to be used during pattern matching.
+    This can allow a greater variety in input, for example by removing dashes or spaces.
+    """
+
+    # Pattern explanation:
+    # - (?<![A-Z0-9]): Negative lookbehind - ensures we don't start mid-IBAN
+    # - ([A-Z]{2}[0-9]{2}(?:[ -]?[A-Z0-9]{4}){2,6}): First capture group with
+    #   country code, check digits, and 2-6 groups of 4 alphanumerics
+    # - ((?:[ -]?[A-Z0-9]{4})?): Second optional capture group for 1 more group of 4
+    # - ((?:[ -]?[A-Z0-9]{1,3})?): Third optional capture group for trailing 1-3 chars
+    # - (?![A-Z0-9]): Negative lookahead - ensures we don't end mid-IBAN
+    #
+    # Multiple capture groups enable validation fallback: the __analyze_patterns method
+    # iterates through groups in reverse order (3→2→1), trying progressively shorter
+    # matches. Example: for "IBAN123456 X", tries "IBAN123456 X" (fails validation),
+    # then "IBAN123456" (passes), avoiding false positives from trailing characters.
+    PATTERNS = [
+        Pattern(
+            "IBAN Generic",
+            r"(?<![A-Z0-9])([A-Z]{2}[0-9]{2}(?:[ -]?[A-Z0-9]{4}){2,6})"
+            r"((?:[ -]?[A-Z0-9]{4})?)((?:[ -]?[A-Z0-9]{1,3})?)(?![A-Z0-9])",
+            0.5,
+        ),
+    ]
+
+    CONTEXT = ["iban", "bank", "transaction"]
+
+    LETTERS: Dict[int, str] = {
+        ord(d): str(i) for i, d in enumerate(string.digits + string.ascii_uppercase)
+    }
+
+    def __init__(
+        self,
+        patterns: List[str] = None,
+        context: List[str] = None,
+        supported_language: str = "en",
+        supported_entity: str = "IBAN_CODE",
+        exact_match: bool = False,
+        bos_eos: Tuple[str, str] = (BOS, EOS),
+        regex_flags: int = re.DOTALL | re.MULTILINE,
+        replacement_pairs: Optional[List[Tuple[str, str]]] = None,
+        name: Optional[str] = None,
+    ):
+        self.replacement_pairs = replacement_pairs or [("-", ""), (" ", "")]
+        self.exact_match = exact_match
+        self.BOSEOS = bos_eos if exact_match else ()
+        patterns = patterns if patterns else self.PATTERNS
+        context = context if context else self.CONTEXT
+        super().__init__(
+            supported_entity=supported_entity,
+            patterns=patterns,
+            context=context,
+            supported_language=supported_language,
+            global_regex_flags=regex_flags,
+            name=name,
+        )
+
+    def validate_result(self, pattern_text: str):  # noqa: D102
+        try:
+            pattern_text = EntityRecognizer.sanitize_value(
+                pattern_text, self.replacement_pairs
+            )
+            is_valid_checksum = (
+                self.__generate_iban_check_digits(pattern_text, self.LETTERS)
+                == pattern_text[2:4]
+            )
+            # score = EntityRecognizer.MIN_SCORE
+            result = False
+            if is_valid_checksum:
+                if self.__is_valid_format(pattern_text, self.BOSEOS):
+                    result = True
+                elif self.__is_valid_format(pattern_text.upper(), self.BOSEOS):
+                    result = None
+            return result
+        except ValueError:
+            logger.error("Failed to validate text %s", pattern_text)
+            return False
+
+    def analyze(
+        self,
+        text: str,
+        entities: List[str],
+        nlp_artifacts: NlpArtifacts = None,
+        regex_flags: int = None,
+    ) -> List[RecognizerResult]:
+        """Analyze IBAN."""
+        results = []
+
+        if self.patterns:
+            pattern_result = self.__analyze_patterns(text)
+            results.extend(pattern_result)
+
+        return results
+
+    def __analyze_patterns(self, text: str, flags: int = None):
+        """
+        Evaluate all patterns in the provided text.
+
+        Logic includes detecting words in the provided deny list.
+        In a sentence we could get a false positive at the end of our regex, were we
+        want to find the IBAN but not the false positive at the end of the match.
+
+        i.e. "I want my deposit in DE89370400440532013000 2 days from today."
+
+        :param text: text to analyze
+        :param flags: regex flags
+        :return: A list of RecognizerResult
+        """
+        flags = flags if flags else self.global_regex_flags
+        results = []
+        for pattern in self.patterns:
+            matches = re.finditer(pattern.regex, text, flags=flags)
+
+            for match in matches:
+                for grp_num in reversed(range(1, len(match.groups()) + 1)):
+                    start = match.span(0)[0]
+                    end = (
+                        match.span(grp_num)[1]
+                        if match.span(grp_num)[1] > 0
+                        else match.span(0)[1]
+                    )
+                    current_match = text[start:end]
+
+                    # Skip empty results
+                    if current_match == "":
+                        continue
+
+                    score = pattern.score
+
+                    validation_result = self.validate_result(current_match)
+                    description = PatternRecognizer.build_regex_explanation(
+                        self.name,
+                        pattern.name,
+                        pattern.regex,
+                        score,
+                        validation_result,
+                        flags,
+                    )
+                    pattern_result = RecognizerResult(
+                        entity_type=self.supported_entities[0],
+                        start=start,
+                        end=end,
+                        score=score,
+                        analysis_explanation=description,
+                        recognition_metadata={
+                            RecognizerResult.RECOGNIZER_NAME_KEY: self.name,
+                            RecognizerResult.RECOGNIZER_IDENTIFIER_KEY: self.id,
+                        },
+                    )
+
+                    if validation_result is not None:
+                        if validation_result:
+                            pattern_result.score = EntityRecognizer.MAX_SCORE
+                        else:
+                            pattern_result.score = EntityRecognizer.MIN_SCORE
+
+                    if pattern_result.score > EntityRecognizer.MIN_SCORE:
+                        results.append(pattern_result)
+                        break
+
+        return results
+
+    @staticmethod
+    def __number_iban(iban: str, letters: Dict[int, str]) -> str:
+        return (iban[4:] + iban[:4]).translate(letters)
+
+    @staticmethod
+    def __generate_iban_check_digits(iban: str, letters: Dict[int, str]) -> str:
+        transformed_iban = (iban[:2] + "00" + iban[4:]).upper()
+        number_iban = IbanRecognizer.__number_iban(transformed_iban, letters)
+        return f"{98 - (int(number_iban) % 97):0>2}"
+
+    @staticmethod
+    def __is_valid_format(
+        iban: str,
+        bos_eos: Tuple[str, str] = (BOS, EOS),
+        flags: int = re.DOTALL | re.MULTILINE,
+    ) -> bool:
+        country_code = iban[:2]
+        if country_code in regex_per_country:
+            country_regex = regex_per_country.get(country_code, "")
+            if bos_eos and country_regex:
+                country_regex = bos_eos[0] + country_regex + bos_eos[1]
+            return country_regex and re.match(country_regex, iban, flags=flags)
+
+        return False

package/server/piecemaker/vendor/websocket-server/scripts/presidio_analyzer/predefined_recognizers/generic/ip_recognizer.py

@@ -0,0 +1,65 @@
+import ipaddress
+from typing import List, Optional
+
+from presidio_analyzer import Pattern, PatternRecognizer
+
+
+class IpRecognizer(PatternRecognizer):
+    """
+    Recognize IP address using regex.
+
+    :param patterns: List of patterns to be used by this recognizer
+    :param context: List of context words to increase confidence in detection
+    :param supported_language: Language this recognizer supports
+    :param supported_entity: The entity this recognizer can detect
+    """
+
+    PATTERNS = [
+        Pattern(
+            "IPv4",
+            r"\b(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\b",
+            0.6,
+        ),
+        Pattern(
+            "IPv6",
+            r"\b(([0-9a-fA-F]{1,4}:){7,7}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,7}:|([0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2}|([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3}|([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4}|([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:((:[0-9a-fA-F]{1,4}){1,6})|:((:[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(:[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]{1,}|::(ffff(:0{1,4}){0,1}:){0,1}((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])|([0-9a-fA-F]{1,4}:){1,4}:((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9]))\b",
+            0.6,
+        ),
+        Pattern(
+            "IPv6",
+            r"::",
+            0.1,
+        ),
+    ]
+
+    CONTEXT = ["ip", "ipv4", "ipv6"]
+
+    def __init__(
+        self,
+        patterns: Optional[List[Pattern]] = None,
+        context: Optional[List[str]] = None,
+        supported_language: str = "en",
+        supported_entity: str = "IP_ADDRESS",
+        name: Optional[str] = None,
+    ):
+        patterns = patterns if patterns else self.PATTERNS
+        context = context if context else self.CONTEXT
+        super().__init__(
+            supported_entity=supported_entity,
+            patterns=patterns,
+            context=context,
+            supported_language=supported_language,
+            name=name,
+        )
+
+    def invalidate_result(self, pattern_text: str) -> bool:
+        """
+        Check if the pattern text cannot be validated as an IP address.
+
+        :param pattern_text: Text detected as pattern by regex
+        :return: True if invalidated
+        """
+        try:
+            ipaddress.ip_address(pattern_text)
+        except ValueError:
+            return True

package/server/piecemaker/vendor/websocket-server/scripts/presidio_analyzer/predefined_recognizers/generic/mac_recognizer.py

@@ -0,0 +1,73 @@
+import re
+from typing import List, Optional
+
+from presidio_analyzer import Pattern, PatternRecognizer
+
+
+class MacAddressRecognizer(PatternRecognizer):
+    """
+    Recognize MAC (Media Access Control) address using regex.
+
+    Supports three common MAC address formats:
+    - Colon-separated: 00:1A:2B:3C:4D:5E
+    - Hyphen-separated: 00-1A-2B-3C-4D-5E
+    - Cisco format (dot-separated groups of 4): 0012.3456.789A
+
+    ref :
+    - https://en.wikipedia.org/wiki/MAC_address#Notational_conventions
+    - https://www.ieee802.org/1/files/public/docs2020/yangsters-smansfield-mac-address-format-0420-v01.pdf
+    """
+
+    PATTERNS = [
+        Pattern(
+            "MAC_COLON_OR_HYPHEN",
+            r"\b[0-9A-Fa-f]{2}([:-])(?:[0-9A-Fa-f]{2}\1){4}[0-9A-Fa-f]{2}\b",
+            0.6,
+        ),
+        Pattern(
+            "MAC_CISCO_DOT",
+            r"\b[0-9A-Fa-f]{4}\.[0-9A-Fa-f]{4}\.[0-9A-Fa-f]{4}\b",
+            0.6,
+        ),
+    ]
+
+    CONTEXT = ["mac", "mac address", "hardware address", "physical address", "ethernet"]
+
+    def __init__(
+        self,
+        patterns: Optional[List[Pattern]] = None,
+        context: Optional[List[str]] = None,
+        supported_language: str = "en",
+        supported_entity: str = "MAC_ADDRESS",
+        name: Optional[str] = None,
+    ):
+        patterns = patterns if patterns else self.PATTERNS
+        context = context if context else self.CONTEXT
+        super().__init__(
+            supported_entity=supported_entity,
+            patterns=patterns,
+            context=context,
+            supported_language=supported_language,
+            name=name
+        )
+
+    def invalidate_result(self, pattern_text: str) -> bool:
+        """
+        Check if the pattern text is a valid MAC address format.
+
+        :param pattern_text: Text detected as pattern by regex
+        :return: True if invalidated (invalid MAC address)
+        """
+        # Remove separators and validate hex characters and length
+        cleaned = re.sub(r'[:\-.]', '', pattern_text)
+
+        # All characters must be valid hex
+        if re.fullmatch(r"[0-9A-Fa-f]{12}", cleaned) is None:
+            return True
+
+        # Optionally reject broadcast/multicast addresses if needed
+        # Broadcast: FF:FF:FF:FF:FF:FF
+        if cleaned.upper() == 'FFFFFFFFFFFF' or cleaned.upper() == '000000000000':
+            return True
+
+        return False

package/server/piecemaker/vendor/websocket-server/scripts/presidio_analyzer/predefined_recognizers/generic/url_recognizer.py

@@ -0,0 +1,50 @@
+from typing import List, Optional
+
+from presidio_analyzer import Pattern, PatternRecognizer
+
+
+class UrlRecognizer(PatternRecognizer):
+    """
+    Recognize urls using regex.
+
+    This application uses Open Source components:
+    Project: CommonRegex https://github.com/madisonmay/CommonRegex
+    Copyright (c) 2014 Madison May
+    License (MIT)  https://github.com/madisonmay/CommonRegex/blob/master/LICENSE
+
+    :param patterns: List of patterns to be used by this recognizer
+    :param context: List of context words to increase confidence in detection
+    :param supported_language: Language this recognizer supports
+    :param supported_entity: The entity this recognizer can detect
+    """
+
+    BASE_URL_REGEX = r"((www\d{0,3}[.])?[a-z0-9.\-]+[.](?:(?:com)|(?:edu)|(?:gov)|(?:int)|(?:mil)|(?:net)|(?:onl)|(?:org)|(?:pro)|(?:red)|(?:tel)|(?:uno)|(?:xxx)|(?:academy)|(?:accountant)|(?:accountants)|(?:actor)|(?:adult)|(?:africa)|(?:agency)|(?:airforce)|(?:apartments)|(?:app)|(?:archi)|(?:army)|(?:art)|(?:asia)|(?:associates)|(?:attorney)|(?:auction)|(?:audio)|(?:auto)|(?:autos)|(?:baby)|(?:band)|(?:bar)|(?:bargains)|(?:beer)|(?:berlin)|(?:best)|(?:bet)|(?:bid)|(?:bike)|(?:bio)|(?:black)|(?:blackfriday)|(?:blog)|(?:blue)|(?:boats)|(?:bond)|(?:boo)|(?:boston)|(?:bot)|(?:boutique)|(?:build)|(?:builders)|(?:business)|(?:buzz)|(?:cab)|(?:cafe)|(?:cam)|(?:camera)|(?:camp)|(?:capital)|(?:car)|(?:cards)|(?:care)|(?:careers)|(?:cars)|(?:casa)|(?:cash)|(?:casino)|(?:catering)|(?:center)|(?:ceo)|(?:cfd)|(?:charity)|(?:chat)|(?:cheap)|(?:christmas)|(?:church)|(?:city)|(?:claims)|(?:cleaning)|(?:click)|(?:clinic)|(?:clothing)|(?:cloud)|(?:club)|(?:codes)|(?:coffee)|(?:college)|(?:com)|(?:community)|(?:company)|(?:computer)|(?:condos)|(?:construction)|(?:consulting)|(?:contact)|(?:contractors)|(?:cooking)|(?:cool)|(?:coupons)|(?:courses)|(?:credit)|(?:creditcard)|(?:cricket)|(?:cruises)|(?:cyou)|(?:dad)|(?:dance)|(?:date)|(?:dating)|(?:day)|(?:degree)|(?:delivery)|(?:democrat)|(?:dental)|(?:dentist)|(?:desi)|(?:design)|(?:dev)|(?:diamonds)|(?:diet)|(?:digital)|(?:direct)|(?:directory)|(?:discount)|(?:doctor)|(?:dog)|(?:domains)|(?:download)|(?:earth)|(?:eco)|(?:education)|(?:email)|(?:energy)|(?:engineer)|(?:engineering)|(?:enterprises)|(?:equipment)|(?:esq)|(?:estate)|(?:events)|(?:exchange)|(?:expert)|(?:exposed)|(?:express)|(?:fail)|(?:faith)|(?:family)|(?:fans)|(?:farm)|(?:fashion)|(?:feedback)|(?:film)|(?:finance)|(?:financial)|(?:fish)|(?:fishing)|(?:fit)|(?:fitness)|(?:flights)|(?:florist)|(?:flowers)|(?:football)|(?:forsale)|(?:foundation)|(?:fun)|(?:fund)|(?:furniture)|(?:futbol)|(?:fyi)|(?:gallery)|(?:game)|(?:games)|(?:garden)|(?:gay)|(?:gdn)|(?:gifts)|(?:gives)|(?:giving)|(?:glass)|(?:global)|(?:gmbh)|(?:gold)|(?:golf)|(?:graphics)|(?:gratis)|(?:green)|(?:gripe)|(?:group)|(?:guide)|(?:guitars)|(?:guru)|(?:hair)|(?:hamburg)|(?:haus)|(?:health)|(?:healthcare)|(?:help)|(?:hiphop)|(?:hockey)|(?:holdings)|(?:holiday)|(?:homes)|(?:horse)|(?:hospital)|(?:host)|(?:hosting)|(?:house)|(?:how)|(?:icu)|(?:info)|(?:ink)|(?:institute)|(?:insure)|(?:international)|(?:investments)|(?:irish)|(?:jewelry)|(?:jetzt)|(?:juegos)|(?:kaufen)|(?:kids)|(?:kitchen)|(?:kiwi)|(?:krd)|(?:kyoto)|(?:land)|(?:lat)|(?:law)|(?:lawyer)|(?:lease)|(?:legal)|(?:lgbt)|(?:life)|(?:lighting)|(?:limited)|(?:limo)|(?:link)|(?:live)|(?:loan)|(?:loans)|(?:lol)|(?:london)|(?:love)|(?:ltd)|(?:ltda)|(?:luxury)|(?:maison)|(?:management)|(?:market)|(?:marketing)|(?:markets)|(?:mba)|(?:media)|(?:melbourne)|(?:meme)|(?:memorial)|(?:men)|(?:miami)|(?:mobi)|(?:moda)|(?:moe)|(?:mom)|(?:money)|(?:monster)|(?:mortgage)|(?:motorcycles)|(?:mov)|(?:movie)|(?:nagoya)|(?:name)|(?:navy)|(?:network)|(?:new)|(?:news)|(?:ngo)|(?:ninja)|(?:now)|(?:nyc)|(?:observer)|(?:okinawa)|(?:one)|(?:ong)|(?:onl)|(?:online)|(?:organic)|(?:osaka)|(?:page)|(?:paris)|(?:partners)|(?:parts)|(?:party)|(?:pet)|(?:phd)|(?:photo)|(?:photography)|(?:photos)|(?:pics)|(?:pictures)|(?:pink)|(?:pizza)|(?:place)|(?:plumbing)|(?:plus)|(?:poker)|(?:porn)|(?:press)|(?:pro)|(?:productions)|(?:prof)|(?:promo)|(?:properties)|(?:property)|(?:protection)|(?:pub)|(?:quest)|(?:racing)|(?:recipes)|(?:red)|(?:rehab)|(?:reise)|(?:reisen)|(?:rent)|(?:rentals)|(?:repair)|(?:report)|(?:republican)|(?:rest)|(?:restaurant)|(?:review)|(?:reviews)|(?:rip)|(?:rocks)|(?:rodeo)|(?:rsvp)|(?:run)|(?:saarland)|(?:sale)|(?:salon)|(?:sarl)|(?:sbs)|(?:school)|(?:schule)|(?:science)|(?:services)|(?:sex)|(?:sexy)|(?:sh)|(?:shoes)|(?:shop)|(?:shopping)|(?:show)|(?:singles)|(?:site)|(?:skin)|(?:soccer)|(?:social)|(?:software)|(?:solar)|(?:solutions)|(?:soy)|(?:space)|(?:spiegel)|(?:study)|(?:style)|(?:sucks)|(?:supply)|(?:support)|(?:surf)|(?:surgery)|(?:systems)|(?:tax)|(?:taxi)|(?:team)|(?:tech)|(?:technology)|(?:tel)|(?:theater)|(?:tips)|(?:tires)|(?:today)|(?:tools)|(?:top)|(?:tours)|(?:town)|(?:toys)|(?:trade)|(?:training)|(?:tube)|(?:uk)|(?:university)|(?:uno)|(?:vacations)|(?:ventures)|(?:vet)|(?:video)|(?:villas)|(?:vin)|(?:vip)|(?:vision)|(?:vlaanderen)|(?:vodka)|(?:vote)|(?:voting)|(?:voyage)|(?:wales)|(?:wang)|(?:watch)|(?:webcam)|(?:website)|(?:wedding)|(?:wiki)|(?:wine)|(?:work)|(?:works)|(?:world)|(?:wtf)|(?:xyz)|(?:yoga)|(?:yokohama)|(?:you)|(?:zone)|(?:ac)|(?:ad)|(?:ae)|(?:af)|(?:ag)|(?:ai)|(?:al)|(?:am)|(?:an)|(?:ao)|(?:aq)|(?:ar)|(?:as)|(?:at)|(?:au)|(?:aw)|(?:ax)|(?:az)|(?:ba)|(?:bb)|(?:bd)|(?:be)|(?:bf)|(?:bg)|(?:bh)|(?:bi)|(?:bj)|(?:bm)|(?:bn)|(?:bo)|(?:br)|(?:bs)|(?:bt)|(?:bv)|(?:bw)|(?:by)|(?:bz)|(?:ca)|(?:cc)|(?:cd)|(?:cf)|(?:cg)|(?:ch)|(?:ci)|(?:ck)|(?:cl)|(?:cm)|(?:cn)|(?:co)|(?:cr)|(?:cu)|(?:cv)|(?:cw)|(?:cx)|(?:cy)|(?:cz)|(?:de)|(?:dj)|(?:dk)|(?:dm)|(?:do)|(?:dz)|(?:ec)|(?:ee)|(?:eg)|(?:er)|(?:es)|(?:et)|(?:eu)|(?:fi)|(?:fj)|(?:fk)|(?:fm)|(?:fo)|(?:fr)|(?:ga)|(?:gb)|(?:gd)|(?:ge)|(?:gf)|(?:gg)|(?:gh)|(?:gi)|(?:gl)|(?:gm)|(?:gn)|(?:gp)|(?:gq)|(?:gr)|(?:gs)|(?:gt)|(?:gu)|(?:gw)|(?:gy)|(?:hk)|(?:hm)|(?:hn)|(?:hr)|(?:ht)|(?:hu)|(?:id)|(?:ie)|(?:il)|(?:im)|(?:in)|(?:io)|(?:iq)|(?:ir)|(?:is)|(?:it)|(?:je)|(?:jm)|(?:jo)|(?:jp)|(?:ke)|(?:kg)|(?:kh)|(?:ki)|(?:km)|(?:kn)|(?:kp)|(?:kr)|(?:kw)|(?:ky)|(?:kz)|(?:la)|(?:lb)|(?:lc)|(?:li)|(?:lk)|(?:lr)|(?:ls)|(?:lt)|(?:lu)|(?:lv)|(?:ly)|(?:ma)|(?:mc)|(?:md)|(?:me)|(?:mg)|(?:mh)|(?:mk)|(?:ml)|(?:mm)|(?:mn)|(?:mo)|(?:mp)|(?:mq)|(?:mr)|(?:ms)|(?:mt)|(?:mu)|(?:mv)|(?:mw)|(?:mx)|(?:my)|(?:mz)|(?:na)|(?:nc)|(?:ne)|(?:nf)|(?:ng)|(?:ni)|(?:nl)|(?:no)|(?:np)|(?:nr)|(?:nu)|(?:nz)|(?:om)|(?:pa)|(?:pe)|(?:pf)|(?:pg)|(?:ph)|(?:pk)|(?:pl)|(?:pm)|(?:pn)|(?:pr)|(?:ps)|(?:pt)|(?:pw)|(?:py)|(?:qa)|(?:re)|(?:ro)|(?:rs)|(?:ru)|(?:rw)|(?:sa)|(?:sb)|(?:sc)|(?:sd)|(?:se)|(?:sg)|(?:sh)|(?:si)|(?:sj)|(?:sk)|(?:sl)|(?:sm)|(?:sn)|(?:so)|(?:sr)|(?:st)|(?:su)|(?:sv)|(?:sx)|(?:sy)|(?:sz)|(?:tc)|(?:td)|(?:tf)|(?:tg)|(?:th)|(?:tj)|(?:tk)|(?:tl)|(?:tm)|(?:tn)|(?:to)|(?:tp)|(?:tr)|(?:tt)|(?:tv)|(?:tw)|(?:tz)|(?:ua)|(?:ug)|(?:uk)|(?:us)|(?:uy)|(?:uz)|(?:va)|(?:vc)|(?:ve)|(?:vg)|(?:vi)|(?:vn)|(?:vu)|(?:wf)|(?:ws)|(?:ye)|(?:yt)|(?:za)|(?:zm)|(?:zw))(?:/[^\s()<>\"']*)?)"  # noqa: E501
+
+    PATTERNS = [
+        Pattern("Standard Url", "(?i)(?:https?://)" + BASE_URL_REGEX, 0.6),
+        Pattern("Non schema URL", "(?i)" + BASE_URL_REGEX, 0.5),
+        Pattern("Quoted URL", r'(?i)["\'](https?://' + BASE_URL_REGEX + r')["\']', 0.6),
+        Pattern(
+            "Quoted Non-schema URL", r'(?i)["\'](' + BASE_URL_REGEX + r')["\']', 0.5
+        ),
+    ]
+
+    CONTEXT = ["url", "website", "link"]
+
+    def __init__(
+        self,
+        patterns: Optional[List[Pattern]] = None,
+        context: Optional[List[str]] = None,
+        supported_language: str = "en",
+        supported_entity: str = "URL",
+        name: Optional[str] = None,
+    ):
+        patterns = patterns if patterns else self.PATTERNS
+        context = context if context else self.CONTEXT
+        super().__init__(
+            supported_entity=supported_entity,
+            patterns=patterns,
+            context=context,
+            supported_language=supported_language,
+            name=name,
+        )