Skip to content

String Milestones¤

Class for handling text string milestones.

StringMilestones pydantic-model ¤

Bases: BaseModel

String Milestones class.

Milestones object for text strings or spaCy Doc objects to be treated as strings.

Config:

  • arbitrary_types_allowed: True
  • json_schema_extra: DocJSONSchema.schema()

Fields:

  • doc (Doclike)
  • patterns (str | list[str])
  • case_sensitive (bool)
  • flags (Enum)
  • _spans (list)
Source code in lexos/milestones/string_milestones.py 
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
class StringMilestones(BaseModel):
    """String Milestones class.

    Milestones object for text strings or spaCy Doc objects to
    be treated as strings.
    """

    doc: Doclike = Field(
        json_schema_extra={"description": "A string or spaCy Doc object."}
    )

    patterns: str | list[str] = Field(
        default=None,
        json_schema_extra={"description": "The pattern(s) used to match milestones."},
    )
    case_sensitive: bool = Field(
        default=True,
        json_schema_extra={
            "description": "Whether to perform case-sensitive searches."
        },
    )
    flags: Enum = Field(
        default=case_sensitive_flags,
        json_schema_extra={"description": "The regex flags to use."},
    )

    model_config = ConfigDict(
        arbitrary_types_allowed=True, json_schema_extra=DocJSONSchema.schema()
    )

    def __init__(self, **data) -> None:
        """Set regex flags and milestone IOB extensions after initialization."""
        super().__init__(**data)
        self._spans: list = []
        if not self.case_sensitive:
            self.flags = case_insensitive_flags
        self.patterns = ensure_list(self.patterns)
        if self.patterns != [None]:
            self.set()

    @property
    def spans(self) -> list[StringSpan]:
        """Return the Spans.

        Returns:
            list[StringSpan]: A list of StringSpans.
        """
        return self._spans or []

    def __iter__(self) -> Iterator:
        """Make the class iterable.

        Returns:
            Iterator: A generator containing the object's spans.
        """
        return (span for span in self.spans)

    def _set_case_sensitivity(self, case_sensitive: Optional[bool] = None) -> None:
        """Set the object's case sensitivity.

        Args:
            case_sensitive (optional, bool): Whether or not to use case-sensitive searching.
        """
        if case_sensitive is not None:
            self.case_sensitive = case_sensitive
        if self.case_sensitive is True:
            self.flags = case_sensitive_flags
        else:
            self.flags = case_insensitive_flags

    @validate_call()
    def set(
        self,
        patterns: Optional[str | list[str]] = None,
        case_sensitive: Optional[bool] = None,
    ) -> None:
        """Return the milestones.

        Args:
            patterns (Optional[str | list[str]]): The pattern(s) used to match milestones.
            case_sensitive (bool, optional): Whether to perform case-sensitive searches. Defaults to True.

        Note:
            If no parameters are set, the method will use the object's current patterns and case sensitivity.
        """
        if patterns:
            self.patterns = ensure_list(patterns)
        self._set_case_sensitivity(case_sensitive)
        text = self.doc if isinstance(self.doc, str) else self.doc.text
        all_matches = []
        for pattern in self.patterns:
            matches = re.finditer(pattern, text, self.flags)
            all_matches.extend(
                StringSpan(text=match.group(), start=match.start(), end=match.end())
                for match in matches
            )
        all_matches.sort(key=lambda match: match.start)
        self._spans = all_matches

spans: list[StringSpan] property ¤

Return the Spans.

Returns:

Type Description
list[StringSpan]

list[StringSpan]: A list of StringSpans.

__init__(**data) -> None ¤

Set regex flags and milestone IOB extensions after initialization.

Source code in lexos/milestones/string_milestones.py 
80
81
82
83
84
85
86
87
88
def __init__(self, **data) -> None:
    """Set regex flags and milestone IOB extensions after initialization."""
    super().__init__(**data)
    self._spans: list = []
    if not self.case_sensitive:
        self.flags = case_insensitive_flags
    self.patterns = ensure_list(self.patterns)
    if self.patterns != [None]:
        self.set()

__iter__() -> Iterator ¤

Make the class iterable.

Returns:

Name Type Description
Iterator Iterator

A generator containing the object's spans.
Source code in lexos/milestones/string_milestones.py 
 99
100
101
102
103
104
105
def __iter__(self) -> Iterator:
    """Make the class iterable.

    Returns:
        Iterator: A generator containing the object's spans.
    """
    return (span for span in self.spans)

set(patterns: Optional[str | list[str]] = None, case_sensitive: Optional[bool] = None) -> None ¤

Return the milestones.

Parameters:

Name Type Description Default
patterns Optional[str | list[str]]

The pattern(s) used to match milestones.

 None
case_sensitive bool

Whether to perform case-sensitive searches. Defaults to True.

 None
Note

If no parameters are set, the method will use the object's current patterns and case sensitivity.

Source code in lexos/milestones/string_milestones.py 
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
@validate_call()
def set(
    self,
    patterns: Optional[str | list[str]] = None,
    case_sensitive: Optional[bool] = None,
) -> None:
    """Return the milestones.

    Args:
        patterns (Optional[str | list[str]]): The pattern(s) used to match milestones.
        case_sensitive (bool, optional): Whether to perform case-sensitive searches. Defaults to True.

    Note:
        If no parameters are set, the method will use the object's current patterns and case sensitivity.
    """
    if patterns:
        self.patterns = ensure_list(patterns)
    self._set_case_sensitivity(case_sensitive)
    text = self.doc if isinstance(self.doc, str) else self.doc.text
    all_matches = []
    for pattern in self.patterns:
        matches = re.finditer(pattern, text, self.flags)
        all_matches.extend(
            StringSpan(text=match.group(), start=match.start(), end=match.end())
            for match in matches
        )
    all_matches.sort(key=lambda match: match.start)
    self._spans = all_matches

__init__(**data) -> None ¤

Set regex flags and milestone IOB extensions after initialization.

Source code in lexos/milestones/string_milestones.py 
80
81
82
83
84
85
86
87
88
def __init__(self, **data) -> None:
    """Set regex flags and milestone IOB extensions after initialization."""
    super().__init__(**data)
    self._spans: list = []
    if not self.case_sensitive:
        self.flags = case_insensitive_flags
    self.patterns = ensure_list(self.patterns)
    if self.patterns != [None]:
        self.set()

__iter__() -> Iterator ¤

Make the class iterable.

Returns:

Name Type Description
Iterator Iterator

A generator containing the object's spans.
Source code in lexos/milestones/string_milestones.py 
 99
100
101
102
103
104
105
def __iter__(self) -> Iterator:
    """Make the class iterable.

    Returns:
        Iterator: A generator containing the object's spans.
    """
    return (span for span in self.spans)

spans: list[StringSpan] property ¤

Return the Spans.

Returns:

Type Description
list[StringSpan]

list[StringSpan]: A list of StringSpans.

_set_case_sensitivity(case_sensitive: Optional[bool] = None) -> None ¤

Set the object's case sensitivity.

Parameters:

Name Type Description Default
case_sensitive (optional, bool)

Whether or not to use case-sensitive searching.

 None
Source code in lexos/milestones/string_milestones.py 
107
108
109
110
111
112
113
114
115
116
117
118
def _set_case_sensitivity(self, case_sensitive: Optional[bool] = None) -> None:
    """Set the object's case sensitivity.

    Args:
        case_sensitive (optional, bool): Whether or not to use case-sensitive searching.
    """
    if case_sensitive is not None:
        self.case_sensitive = case_sensitive
    if self.case_sensitive is True:
        self.flags = case_sensitive_flags
    else:
        self.flags = case_insensitive_flags

set(patterns: Optional[str | list[str]] = None, case_sensitive: Optional[bool] = None) -> None ¤

Return the milestones.

Parameters:

Name Type Description Default
patterns Optional[str | list[str]]

The pattern(s) used to match milestones.

 None
case_sensitive bool

Whether to perform case-sensitive searches. Defaults to True.

 None
Note

If no parameters are set, the method will use the object's current patterns and case sensitivity.

Source code in lexos/milestones/string_milestones.py 
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
@validate_call()
def set(
    self,
    patterns: Optional[str | list[str]] = None,
    case_sensitive: Optional[bool] = None,
) -> None:
    """Return the milestones.

    Args:
        patterns (Optional[str | list[str]]): The pattern(s) used to match milestones.
        case_sensitive (bool, optional): Whether to perform case-sensitive searches. Defaults to True.

    Note:
        If no parameters are set, the method will use the object's current patterns and case sensitivity.
    """
    if patterns:
        self.patterns = ensure_list(patterns)
    self._set_case_sensitivity(case_sensitive)
    text = self.doc if isinstance(self.doc, str) else self.doc.text
    all_matches = []
    for pattern in self.patterns:
        matches = re.finditer(pattern, text, self.flags)
        all_matches.extend(
            StringSpan(text=match.group(), start=match.start(), end=match.end())
            for match in matches
        )
    all_matches.sort(key=lambda match: match.start)
    self._spans = all_matches

StringSpan pydantic-model ¤

Bases: BaseModel

StringSpan class.

A Pydantic model containing the milestone text, and the start and character indices of the milestone in the original text.

Fields:

  • text (str)
  • start (int)
  • end (int)
Source code in lexos/milestones/string_milestones.py 
38
39
40
41
42
43
44
45
46
47
class StringSpan(BaseModel):
    """StringSpan class.

    A Pydantic model containing the milestone text, and the start
    and character indices of the milestone in the original text.
    """

    text: str
    start: int
    end: int