Skip to content

Index

Everything related to the TIM language.

AliasToken dataclass

Bases: Token

A way to reference a set of tags from one central name.

Source code in pytermgui/markup/tokens.py
260
261
262
263
264
265
266
@dataclass(frozen=True, repr=False)
class AliasToken(Token):
    """A way to reference a set of tags from one central name."""

    __slots__ = ("value",)

    value: str

ClearToken dataclass

Bases: Token

A tag-clearer.

These tokens are prefixed by /, and followed by the name of the tag they target.

To reset color information in the current text, use the /fg and /bg special tags. We cannot unset a specific color due to how the terminal works; all these do is "reset" the current stroke color to the default of the terminal.

Additionally, there are some other special identifiers:

  • /: Clears all tags, including styles, colors, macros, links and more.
  • /!: Clears all currently applied macros.
  • /~: Clears all currently applied links.
Source code in pytermgui/markup/tokens.py
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
@dataclass(frozen=True, repr=False)
class ClearToken(Token):
    """A tag-clearer.

    These tokens are prefixed by `/`, and followed by the name of the tag they target.

    To reset color information in the current text, use the `/fg` and `/bg` special
    tags. We cannot unset a specific color due to how the terminal works; all these do
    is "reset" the current stroke color to the default of the terminal.

    Additionally, there are some other special identifiers:

    - `/`:  Clears all tags, including styles, colors, macros, links and more.
    - `/!`: Clears all currently applied macros.
    - `/~`: Clears all currently applied links.
    """

    __slots__ = ("value",)

    value: str

    @cached_property
    def prettified_markup(self) -> str:
        target = self.markup[1:]

        return f"[210 strikethrough]/[/fg]{target}[/]"

    def __eq__(self, other: object) -> bool:
        if not isinstance(other, Token):
            return False

        return super().__eq__(other) or all(
            obj.markup in ["/dim", "/bold"] for obj in [self, other]
        )

    def targets(  # pylint: disable=too-many-return-statements
        self, token: Token
    ) -> bool:
        """Returns True if this token targets the one given as an argument."""

        if token.is_clear() or token.is_cursor():
            return False

        if self.value in ("/", f"/{token.value}"):
            return True

        if token.is_hyperlink() and self.value == "/~":
            return True

        if token.is_macro() and self.value == "/!":
            return True

        if not Token.is_color(token):
            return False

        if self.value == "/fg" and not token.color.background:
            return True

        return self.value == "/bg" and token.color.background

targets(token)

Returns True if this token targets the one given as an argument.

Source code in pytermgui/markup/tokens.py
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
def targets(  # pylint: disable=too-many-return-statements
    self, token: Token
) -> bool:
    """Returns True if this token targets the one given as an argument."""

    if token.is_clear() or token.is_cursor():
        return False

    if self.value in ("/", f"/{token.value}"):
        return True

    if token.is_hyperlink() and self.value == "/~":
        return True

    if token.is_macro() and self.value == "/!":
        return True

    if not Token.is_color(token):
        return False

    if self.value == "/fg" and not token.color.background:
        return True

    return self.value == "/bg" and token.color.background

ColorToken dataclass

Bases: Token

A color identifier.

It stores the markup that created it, as well as the pytermgui.colors.Color object that it represents.

Source code in pytermgui/markup/tokens.py
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
@dataclass(frozen=True, repr=False)
class ColorToken(Token):
    """A color identifier.

    It stores the markup that created it, as well as the `pytermgui.colors.Color` object
    that it represents.
    """

    __slots__ = ("value",)

    value: str
    color: Color

    @cached_property
    def markup(self) -> str:
        return self.color.markup

    @cached_property
    def prettified_markup(self) -> str:
        clearer = "bg" if self.color.background else "fg"

        return f"[{self.markup}]{self.markup}[/{clearer}]"

ContextDict

Bases: TypedDict

A dictionary to hold context about a markup language's environment.

It has two sub-dicts:

  • aliases
  • macros

For information about what they do and contain, see the MarkupLanguage docs.

Source code in pytermgui/markup/parsing.py
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
class ContextDict(TypedDict):
    """A dictionary to hold context about a markup language's environment.

    It has two sub-dicts:

    - aliases
    - macros

    For information about what they do and contain, see the
    [MarkupLanguage docs](/reference/pytermgui/markup/
    language#pytermgui.markup.language.MarkupLanguage).
    """

    aliases: dict[str, str]
    macros: dict[str, MacroType]

CursorToken dataclass

Bases: Token

A cursor location.

These can be used to move the terminal's cursor.

Source code in pytermgui/markup/tokens.py
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
@dataclass(frozen=True, repr=False)
class CursorToken(Token):
    """A cursor location.

    These can be used to move the terminal's cursor.
    """

    __slots__ = ("value", "y", "x")

    value: str
    y: int | None
    x: int | None

    def __iter__(self) -> Iterator[int | None]:
        return iter((self.y, self.x))

    def __repr__(self) -> str:
        return f"<{type(self).__name__} position: {(';'.join(map(str, self)))}>"

    def __fancy_repr__(self) -> Generator[FancyYield, None, None]:
        yield self.__repr__()

    @cached_property
    def markup(self) -> str:
        return f"({self.value})"

HLinkToken dataclass

Bases: Token

A terminal hyperlink.

See https://gist.github.com/egmontkob/eb114294efbcd5adb1944c9f3cb5feda.

Source code in pytermgui/markup/tokens.py
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
@dataclass(frozen=True, repr=False)
class HLinkToken(Token):
    """A terminal hyperlink.

    See https://gist.github.com/egmontkob/eb114294efbcd5adb1944c9f3cb5feda.
    """

    __slots__ = ("value",)

    value: str

    @cached_property
    def markup(self) -> str:
        return f"~{self.value}"

    @cached_property
    def prettified_markup(self) -> str:
        return f"[{self.markup}]~[blue underline]{self.value}[/fg /underline /~]"

MacroToken dataclass

Bases: Token

A binding of a Python function to a markup name.

See the docs on information about syntax & semantics.

Source code in pytermgui/markup/tokens.py
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
@dataclass(frozen=True, repr=False)
class MacroToken(Token):
    """A binding of a Python function to a markup name.

    See the docs on information about syntax & semantics.
    """

    __slots__ = ("value", "arguments")

    value: str
    arguments: tuple[str, ...]

    def __iter__(self) -> Iterator[Any]:
        return iter((self.value, self.arguments))

    @cached_property
    def prettified_markup(self) -> str:
        target = self.markup[1:]

        return f"[210 bold]![/]{target}"

    @cached_property
    def markup(self) -> str:
        return f"{self.value}" + (
            f"({':'.join(self.arguments)})" if len(self.arguments) > 0 else ""
        )

MarkupLanguage

A relatively simple object that binds context to TIM parsing functions.

Most of the job this class has is to pass along a ContextDict to various "lower level" functions, in order to maintain a sort of state. It also exposes ways to modify this state, namely the alias and define methods.

Source code in pytermgui/markup/language.py
 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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
class MarkupLanguage:
    """A relatively simple object that binds context to TIM parsing functions.

    Most of the job this class has is to pass along a `ContextDict` to various
    "lower level" functions, in order to maintain a sort of state. It also exposes
    ways to modify this state, namely the `alias` and `define` methods.
    """

    def __init__(
        self,
        *,
        strict: bool = False,
        default_aliases: bool = True,
        default_macros: bool = True,
    ) -> None:
        self._cache: dict[tuple[str, bool, bool], tuple[str, list[Token], bool]] = {}

        self.context = create_context_dict()
        self._aliases = self.context["aliases"]
        self._macros = self.context["macros"]

        if default_aliases:
            apply_default_aliases(self)

        if default_macros:
            apply_default_macros(self)

        self.strict = strict or STRICT_MARKUP

    @property
    def aliases(self) -> dict[str, str]:
        """Returns a copy of the aliases defined in context."""

        return self._aliases.copy()

    @property
    def macros(self) -> dict[str, MacroType]:
        """Returns a copy of the macros defined in context."""

        return self._macros.copy()

    def clear_cache(self) -> None:
        """Clears the internal cache.

        Use this after re-defining aliases.
        """

        self._cache.clear()

    def define(self, name: str, method: MacroType) -> None:
        """Defines a markup macro.

        Macros are essentially function bindings callable within markup. They can be
        very useful to represent changing data and simplify TIM code.

        Args:
            name: The name that will be used within TIM to call the macro. Must start with
                a bang (`!`).
            method: The function bound to the name given above. This function will take
                any number of strings as arguments, and return a terminal-ready (i.e. parsed)
                string.
        """

        if not name.startswith("!"):
            raise ValueError("TIM macro names must be prefixed by `!`.")

        self._macros[name] = method

    def alias(self, name: str, value: str, *, generate_unsetter: bool = True) -> None:
        """Creates an alias from one custom name to a set of styles.

        These can be used to store and reference a set of tags using only one name.

        Aliases may reference other aliases, but only do this consciously, as it can become
        a hard to follow trail of sorrow very quickly!

        Args:
            name: The name this alias will be referenced by.
            value: The markup value that the alias will represent.
            generate_unsetter: Disable generating clearer aliases.

                For example:
                    ```
                    my-tag = 141 bold italic
                    ```

                will generate:
                    ```
                    /my-tag = /fg /bold /italic
                    ```
        """

        def _generate_unsetter() -> str:
            unsetter = ""
            no_alias = eval_alias(value, self.context)

            for tag in no_alias.split():
                if "(" in tag and ")" in tag:
                    tag = tag[: tag.find("(")]

                if tag in self._aliases or tag in self._macros:
                    unsetter += f" /{tag}"
                    continue

                try:
                    color = str_to_color(tag)
                    unsetter += f" /{'bg' if color.background else 'fg'}"

                except ColorSyntaxError:
                    unsetter += f" /{tag}"

            return unsetter.lstrip(" ")

        self._aliases[name] = value

        if generate_unsetter:
            self._aliases[f"/{name}"] = _generate_unsetter()

    def alias_multiple(self, *, generate_unsetter: bool = True, **items: str) -> None:
        """Runs `MarkupLanguage.alias` repeatedly for all arguments.

        The same `generate_unsetter` value will be used for all calls.

        You can use this in two forms:

        - Traditional keyword arguments:

            ```python
            lang.alias_multiple(my-tag1="bold", my-tag2="italic")
            ```

        - Keyword argument unpacking:

            ```python
            my_aliases = {"my-tag1": "bold", "my-tag2": "italic"}
            lang.alias_multiple(**my_aliases)
            ```
        """

        for name, value in items.items():
            self.alias(name, value, generate_unsetter=generate_unsetter)

    def parse(
        self,
        text: str,
        optimize: bool = False,
        append_reset: bool = True,
    ) -> str:
        """Parses some markup text.

        This is a thin wrapper around [markup.parsing.parse](/reference/
        pytermgui/markup/parsing#pytermgui.markup.parsing.parse). The main additions
        of this wrapper are a caching system, as well as state management.

        Ignoring caching, all calls to this function would be equivalent to:

        ```python3
        def parse(self, *args, **kwargs) -> str:
            kwargs["context"] = self.context

            return parse(*args, **kwargs)
        ```
        """

        key = (text, optimize, append_reset)

        cache_hit = self._cache.get(key)
        if cache_hit is not None:
            cached, tokens, has_macro = cache_hit

            # Re-parse using known tokens when macro is present
            #
            # This saves a tiny fraction of time (around 0.2ms) when parsing
            # macros, for a loss of an even smaller time for the general,
            # non-macro usecase.
            if has_macro:
                output = parse_tokens(
                    tokens,
                    optimize=optimize,
                    append_reset=append_reset,
                    context=self.context,
                    ignore_unknown_tags=not self.strict,
                )

                return output

            return cached

        tokens = list(tokenize_markup(text))

        output = parse_tokens(
            tokens,
            optimize=optimize,
            append_reset=append_reset,
            context=self.context,
            ignore_unknown_tags=not self.strict,
        )

        has_macro = any(token.is_macro() for token in tokens)

        self._cache[key] = (output, tokens, has_macro)

        return output

    # TODO: This should be deprecated.
    @staticmethod
    def get_markup(text: str) -> str:
        """DEPRECATED: Convert ANSI text into markup.

        This function does not use context, and thus is out of place here.
        """

        return tokens_to_markup(list(tokenize_ansi(text)))

    def group_styles(
        self, text: str, tokenizer: Tokenizer = tokenize_ansi
    ) -> Generator[StyledText, None, None]:
        """Generate StyledText-s from some text, using our context.

        See `StyledText.group_styles` for arguments.
        """

        yield from StyledText.group_styles(
            text, tokenizer=tokenizer, context=self.context
        )

    def print(self, *args, **kwargs) -> None:
        """Parse all arguments and pass them through to print, along with kwargs."""

        parsed = []
        for arg in args:
            parsed.append(self.parse(str(arg)))

        get_terminal().print(*parsed, **kwargs)

aliases property

Returns a copy of the aliases defined in context.

macros property

Returns a copy of the macros defined in context.

alias(name, value, *, generate_unsetter=True)

Creates an alias from one custom name to a set of styles.

These can be used to store and reference a set of tags using only one name.

Aliases may reference other aliases, but only do this consciously, as it can become a hard to follow trail of sorrow very quickly!

Parameters:

Name Type Description Default
name str

The name this alias will be referenced by.

required
value str

The markup value that the alias will represent.

required
generate_unsetter bool

Disable generating clearer aliases.

For example:

my-tag = 141 bold italic

will generate:

/my-tag = /fg /bold /italic

True
Source code in pytermgui/markup/language.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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
def alias(self, name: str, value: str, *, generate_unsetter: bool = True) -> None:
    """Creates an alias from one custom name to a set of styles.

    These can be used to store and reference a set of tags using only one name.

    Aliases may reference other aliases, but only do this consciously, as it can become
    a hard to follow trail of sorrow very quickly!

    Args:
        name: The name this alias will be referenced by.
        value: The markup value that the alias will represent.
        generate_unsetter: Disable generating clearer aliases.

            For example:
                ```
                my-tag = 141 bold italic
                ```

            will generate:
                ```
                /my-tag = /fg /bold /italic
                ```
    """

    def _generate_unsetter() -> str:
        unsetter = ""
        no_alias = eval_alias(value, self.context)

        for tag in no_alias.split():
            if "(" in tag and ")" in tag:
                tag = tag[: tag.find("(")]

            if tag in self._aliases or tag in self._macros:
                unsetter += f" /{tag}"
                continue

            try:
                color = str_to_color(tag)
                unsetter += f" /{'bg' if color.background else 'fg'}"

            except ColorSyntaxError:
                unsetter += f" /{tag}"

        return unsetter.lstrip(" ")

    self._aliases[name] = value

    if generate_unsetter:
        self._aliases[f"/{name}"] = _generate_unsetter()

alias_multiple(*, generate_unsetter=True, **items)

Runs MarkupLanguage.alias repeatedly for all arguments.

The same generate_unsetter value will be used for all calls.

You can use this in two forms:

  • Traditional keyword arguments:

    lang.alias_multiple(my-tag1="bold", my-tag2="italic")
    
  • Keyword argument unpacking:

    my_aliases = {"my-tag1": "bold", "my-tag2": "italic"}
    lang.alias_multiple(**my_aliases)
    
Source code in pytermgui/markup/language.py
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
def alias_multiple(self, *, generate_unsetter: bool = True, **items: str) -> None:
    """Runs `MarkupLanguage.alias` repeatedly for all arguments.

    The same `generate_unsetter` value will be used for all calls.

    You can use this in two forms:

    - Traditional keyword arguments:

        ```python
        lang.alias_multiple(my-tag1="bold", my-tag2="italic")
        ```

    - Keyword argument unpacking:

        ```python
        my_aliases = {"my-tag1": "bold", "my-tag2": "italic"}
        lang.alias_multiple(**my_aliases)
        ```
    """

    for name, value in items.items():
        self.alias(name, value, generate_unsetter=generate_unsetter)

clear_cache()

Clears the internal cache.

Use this after re-defining aliases.

Source code in pytermgui/markup/language.py
93
94
95
96
97
98
99
def clear_cache(self) -> None:
    """Clears the internal cache.

    Use this after re-defining aliases.
    """

    self._cache.clear()

define(name, method)

Defines a markup macro.

Macros are essentially function bindings callable within markup. They can be very useful to represent changing data and simplify TIM code.

Parameters:

Name Type Description Default
name str

The name that will be used within TIM to call the macro. Must start with a bang (!).

required
method MacroType

The function bound to the name given above. This function will take any number of strings as arguments, and return a terminal-ready (i.e. parsed) string.

required
Source code in pytermgui/markup/language.py
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
def define(self, name: str, method: MacroType) -> None:
    """Defines a markup macro.

    Macros are essentially function bindings callable within markup. They can be
    very useful to represent changing data and simplify TIM code.

    Args:
        name: The name that will be used within TIM to call the macro. Must start with
            a bang (`!`).
        method: The function bound to the name given above. This function will take
            any number of strings as arguments, and return a terminal-ready (i.e. parsed)
            string.
    """

    if not name.startswith("!"):
        raise ValueError("TIM macro names must be prefixed by `!`.")

    self._macros[name] = method

get_markup(text) staticmethod

DEPRECATED: Convert ANSI text into markup.

This function does not use context, and thus is out of place here.

Source code in pytermgui/markup/language.py
257
258
259
260
261
262
263
264
@staticmethod
def get_markup(text: str) -> str:
    """DEPRECATED: Convert ANSI text into markup.

    This function does not use context, and thus is out of place here.
    """

    return tokens_to_markup(list(tokenize_ansi(text)))

group_styles(text, tokenizer=tokenize_ansi)

Generate StyledText-s from some text, using our context.

See StyledText.group_styles for arguments.

Source code in pytermgui/markup/language.py
266
267
268
269
270
271
272
273
274
275
276
def group_styles(
    self, text: str, tokenizer: Tokenizer = tokenize_ansi
) -> Generator[StyledText, None, None]:
    """Generate StyledText-s from some text, using our context.

    See `StyledText.group_styles` for arguments.
    """

    yield from StyledText.group_styles(
        text, tokenizer=tokenizer, context=self.context
    )

parse(text, optimize=False, append_reset=True)

Parses some markup text.

This is a thin wrapper around markup.parsing.parse. The main additions of this wrapper are a caching system, as well as state management.

Ignoring caching, all calls to this function would be equivalent to:

def parse(self, *args, **kwargs) -> str:
    kwargs["context"] = self.context

    return parse(*args, **kwargs)
Source code in pytermgui/markup/language.py
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
def parse(
    self,
    text: str,
    optimize: bool = False,
    append_reset: bool = True,
) -> str:
    """Parses some markup text.

    This is a thin wrapper around [markup.parsing.parse](/reference/
    pytermgui/markup/parsing#pytermgui.markup.parsing.parse). The main additions
    of this wrapper are a caching system, as well as state management.

    Ignoring caching, all calls to this function would be equivalent to:

    ```python3
    def parse(self, *args, **kwargs) -> str:
        kwargs["context"] = self.context

        return parse(*args, **kwargs)
    ```
    """

    key = (text, optimize, append_reset)

    cache_hit = self._cache.get(key)
    if cache_hit is not None:
        cached, tokens, has_macro = cache_hit

        # Re-parse using known tokens when macro is present
        #
        # This saves a tiny fraction of time (around 0.2ms) when parsing
        # macros, for a loss of an even smaller time for the general,
        # non-macro usecase.
        if has_macro:
            output = parse_tokens(
                tokens,
                optimize=optimize,
                append_reset=append_reset,
                context=self.context,
                ignore_unknown_tags=not self.strict,
            )

            return output

        return cached

    tokens = list(tokenize_markup(text))

    output = parse_tokens(
        tokens,
        optimize=optimize,
        append_reset=append_reset,
        context=self.context,
        ignore_unknown_tags=not self.strict,
    )

    has_macro = any(token.is_macro() for token in tokens)

    self._cache[key] = (output, tokens, has_macro)

    return output

print(*args, **kwargs)

Parse all arguments and pass them through to print, along with kwargs.

Source code in pytermgui/markup/language.py
278
279
280
281
282
283
284
285
def print(self, *args, **kwargs) -> None:
    """Parse all arguments and pass them through to print, along with kwargs."""

    parsed = []
    for arg in args:
        parsed.append(self.parse(str(arg)))

    get_terminal().print(*parsed, **kwargs)

PlainToken dataclass

Bases: Token

A plain piece of text.

These are the parts of data in-between markup tag groups.

Source code in pytermgui/markup/tokens.py
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
@dataclass(frozen=True, repr=False)
class PlainToken(Token):
    """A plain piece of text.

    These are the parts of data in-between markup tag groups.
    """

    __slots__ = ("value",)

    value: str

    def __repr__(self) -> str:
        return f"<{type(self).__name__} markup: {self.markup!r}>"

    def __fancy_repr__(self) -> Generator[FancyYield, None, None]:
        yield f"<{type(self).__name__} markup: {self.markup!r}>"

PseudoToken dataclass

Bases: Token

A token that can modify it's context, but doesn't hold information of its own.

Source code in pytermgui/markup/tokens.py
136
137
138
139
140
141
142
143
144
@dataclass(frozen=True, repr=False)
class PseudoToken(Token):
    """A token that can modify it's context, but doesn't hold information of its own."""

    value: str

    @cached_property
    def prettified_markup(self) -> str:
        return f"[245 italic]{self.markup}[/]"

StyleToken dataclass

Bases: Token

A terminal-style identifier.

Most terminals support a set of 9 styles:

  • bold
  • dim
  • italic
  • underline
  • blink
  • blink2
  • inverse
  • invisible
  • strikethrough

This token will store the style it represents by its name in the value field. Note that other, less widely supported styles may be available; for an up-to-date list, run ptg -i pytermgui.markup.style_maps.STYLES. ```

Source code in pytermgui/markup/tokens.py
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
@dataclass(frozen=True, repr=False)
class StyleToken(Token):
    """A terminal-style identifier.

    Most terminals support a set of 9 styles:

    - bold
    - dim
    - italic
    - underline
    - blink
    - blink2
    - inverse
    - invisible
    - strikethrough

    This token will store the style it represents by its name in the `value` field. Note
    that other, less widely supported styles *may* be available; for an up-to-date list,
    run `ptg -i pytermgui.markup.style_maps.STYLES`.
    ```

    """

    __slots__ = ("value",)

    value: str

StyledText dataclass

An ANSI style-infused string.

This is a sort of helper to handle ANSI texts in a more semantic manner. It keeps track of a sequence and a plain part.

Calling len() will return the length of the printable, non-ANSI part, and indexing will return the characters at the given slice, but also include the sequences that are applied to them.

To generate StyledText-s, it is recommended to use the StyledText.group_styles classmethod.

Source code in pytermgui/markup/language.py
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
@dataclass(frozen=True)
class StyledText:
    """An ANSI style-infused string.

    This is a sort of helper to handle ANSI texts in a more semantic manner. It
    keeps track of a sequence and a plain part.

    Calling `len()` will return the length of the printable, non-ANSI part, and
    indexing will return the characters at the given slice, but also include the
    sequences that are applied to them.

    To generate StyledText-s, it is recommended to use the `StyledText.group_styles`
    classmethod.
    """

    __slots__ = ("plain", "sequences", "tokens", "link", "__dict__")

    sequences: str
    plain: str
    tokens: list[Token]
    link: str | None

    @cached_property
    def foreground(self) -> Color | None:
        """Returns the foreground color of this object."""

        colors = [
            tkn
            for tkn in self.tokens
            if Token.is_color(tkn) and not tkn.color.background
        ]

        if len(colors) == 0:
            return None

        return colors[-1].color

    @cached_property
    def background(self) -> Color | None:
        """Returns the background color of this object."""

        colors = [
            tkn for tkn in self.tokens if Token.is_color(tkn) and tkn.color.background
        ]

        if len(colors) == 0:
            return None

        return colors[-1].color

    @cached_property
    def bold(self) -> bool:
        """Returns this text is bold."""

        return any(Token.is_style(tkn) and tkn.markup == "bold" for tkn in self.tokens)

    @cached_property
    def dim(self) -> bool:
        """Returns this text is dimmed."""

        return any(Token.is_style(tkn) and tkn.markup == "dim" for tkn in self.tokens)

    @cached_property
    def italic(self) -> bool:
        """Returns this text is italicized."""

        return any(
            Token.is_style(tkn) and tkn.markup == "italic" for tkn in self.tokens
        )

    @cached_property
    def underline(self) -> bool:
        """Returns this text is underlined."""

        return any(
            Token.is_style(tkn) and tkn.markup == "underline" for tkn in self.tokens
        )

    @cached_property
    def blink(self) -> bool:
        """Returns this text is blinking."""

        return any(Token.is_style(tkn) and tkn.markup == "blink" for tkn in self.tokens)

    @cached_property
    def blink2(self) -> bool:
        """Returns this text is alternate-blinking."""

        return any(
            Token.is_style(tkn) and tkn.markup == "blink2" for tkn in self.tokens
        )

    @cached_property
    def strikethrough(self) -> bool:
        """Returns this text is striked out."""

        return any(
            Token.is_style(tkn) and tkn.markup == "strikethrough" for tkn in self.tokens
        )

    @cached_property
    def inverse(self) -> bool:
        """Returns this text has its colors inversed."""

        return any(
            Token.is_style(tkn) and tkn.markup == "inverse" for tkn in self.tokens
        )

    @cached_property
    def overline(self) -> bool:
        """Returns this text is overlined."""

        return any(
            Token.is_style(tkn) and tkn.markup == "overline" for tkn in self.tokens
        )

    @staticmethod
    def group_styles(
        text: str,
        tokenizer: Tokenizer = tokenize_ansi,
        context: ContextDict | None = None,
    ) -> Generator[StyledText, None, None]:
        """Yields StyledTexts from an ANSI coded string.

        A new StyledText will be created each time a non-plain token follows a
        plain token, thus all texts will represent a single (ANSI)PLAIN group
        of characters.
        """

        context = context if context is not None else create_context_dict()

        parsers = PARSERS
        link = None

        def _parse(token: Token) -> str:
            nonlocal link

            if token.is_macro():
                return token.markup

            if token.is_hyperlink():
                link = token
                return ""

            if link is not None and Token.is_clear(token) and token.targets(link):
                link = None

            if token.is_clear() and token.value not in CLEARERS:
                return token.markup

            # The full text (last arg) is not relevant here, as ANSI parsing doesn't
            # use any context-defined tags, so no errors will occur.
            return parsers[type(token)](token, context, lambda: "")  # type: ignore

        tokens: list[Token] = []
        token: Token

        for token in tokenizer(text):
            if token.is_plain():
                yield StyledText(
                    "".join(_parse(tkn) for tkn in tokens),
                    token.value,
                    tokens + [token],
                    link.value if link is not None else None,
                )

                tokens = [tkn for tkn in tokens if not tkn.is_cursor()]
                continue

            if Token.is_clear(token):
                tokens = [tkn for tkn in tokens if not token.targets(tkn)]

                if len(tokens) > 0 and tokens[-1] == token:
                    continue

            if len(tokens) > 0 and all(tkn.is_clear() for tkn in tokens):
                tokens = []

            tokens.append(token)

        # if len(tokens) > 0:
        #     token = PlainToken("")

        #     yield StyledText(
        #         "".join(_parse(tkn) for tkn in tokens),
        #         token.value,
        #         tokens + [token],
        #         link.value if link is not None else None,
        #     )

    @classmethod
    def first_of(cls, text: str) -> StyledText | None:
        """Returns the first element of cls.group_styles(text)."""

        for item in cls.group_styles(text):
            return item

        return None

    def __len__(self) -> int:
        return len(self.plain)

    def __str__(self) -> str:
        return self.sequences + self.plain

    def __getitem__(self, sli: int | slice) -> str:
        return self.sequences + self.plain[sli]

background cached property

Returns the background color of this object.

Returns this text is blinking.

blink2 cached property

Returns this text is alternate-blinking.

bold cached property

Returns this text is bold.

dim cached property

Returns this text is dimmed.

foreground cached property

Returns the foreground color of this object.

inverse cached property

Returns this text has its colors inversed.

italic cached property

Returns this text is italicized.

overline cached property

Returns this text is overlined.

strikethrough cached property

Returns this text is striked out.

underline cached property

Returns this text is underlined.

first_of(text) classmethod

Returns the first element of cls.group_styles(text).

Source code in pytermgui/markup/language.py
481
482
483
484
485
486
487
488
@classmethod
def first_of(cls, text: str) -> StyledText | None:
    """Returns the first element of cls.group_styles(text)."""

    for item in cls.group_styles(text):
        return item

    return None

group_styles(text, tokenizer=tokenize_ansi, context=None) staticmethod

Yields StyledTexts from an ANSI coded string.

A new StyledText will be created each time a non-plain token follows a plain token, thus all texts will represent a single (ANSI)PLAIN group of characters.

Source code in pytermgui/markup/language.py
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
@staticmethod
def group_styles(
    text: str,
    tokenizer: Tokenizer = tokenize_ansi,
    context: ContextDict | None = None,
) -> Generator[StyledText, None, None]:
    """Yields StyledTexts from an ANSI coded string.

    A new StyledText will be created each time a non-plain token follows a
    plain token, thus all texts will represent a single (ANSI)PLAIN group
    of characters.
    """

    context = context if context is not None else create_context_dict()

    parsers = PARSERS
    link = None

    def _parse(token: Token) -> str:
        nonlocal link

        if token.is_macro():
            return token.markup

        if token.is_hyperlink():
            link = token
            return ""

        if link is not None and Token.is_clear(token) and token.targets(link):
            link = None

        if token.is_clear() and token.value not in CLEARERS:
            return token.markup

        # The full text (last arg) is not relevant here, as ANSI parsing doesn't
        # use any context-defined tags, so no errors will occur.
        return parsers[type(token)](token, context, lambda: "")  # type: ignore

    tokens: list[Token] = []
    token: Token

    for token in tokenizer(text):
        if token.is_plain():
            yield StyledText(
                "".join(_parse(tkn) for tkn in tokens),
                token.value,
                tokens + [token],
                link.value if link is not None else None,
            )

            tokens = [tkn for tkn in tokens if not tkn.is_cursor()]
            continue

        if Token.is_clear(token):
            tokens = [tkn for tkn in tokens if not token.targets(tkn)]

            if len(tokens) > 0 and tokens[-1] == token:
                continue

        if len(tokens) > 0 and all(tkn.is_clear() for tkn in tokens):
            tokens = []

        tokens.append(token)

Token

A piece of markup information.

All tokens must have at least a value field, and have markup and prettified_markup properties derived from it in some manner.

They are meant to be immutable (frozen), and generated by some tokenization. They are also static representations of the data in its pre-parsed form.

Source code in pytermgui/markup/tokens.py
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 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
class Token:
    """A piece of markup information.

    All tokens must have at least a `value` field, and have `markup` and `prettified_markup`
    properties derived from it in some manner.

    They are meant to be immutable (frozen), and generated by some tokenization. They are also
    static representations of the data in its pre-parsed form.
    """

    value: str

    @cached_property
    def markup(self) -> str:
        """Returns markup representing this token."""

        return self.value

    @cached_property
    def prettified_markup(self) -> str:
        """Returns syntax-highlighted markup representing this token."""

        return f"[{self.markup}]{self.markup}[/{self.markup}]"

    def __eq__(self, other: object) -> bool:
        return isinstance(other, type(self)) and other.value == self.value

    def __repr__(self) -> str:
        return f"<{type(self).__name__} markup: '{self.markup}'>"

    def __fancy_repr__(self) -> Generator[FancyYield, None, None]:
        yield f"<{type(self).__name__} markup: "
        yield {
            "text": self.prettified_markup,
            "highlight": False,
        }
        yield ">"

    def is_plain(self) -> TypeGuard["PlainToken"]:
        """Returns True if this token is an instance of PlainToken."""

        return isinstance(self, PlainToken)

    def is_pseudo(self) -> TypeGuard["PseudoToken"]:
        """Returns True if this token is an instance of PseudoToken."""

        return isinstance(self, PseudoToken)

    def is_color(self) -> TypeGuard["ColorToken"]:
        """Returns True if this token is an instance of ColorToken."""

        return isinstance(self, ColorToken)

    def is_style(self) -> TypeGuard["StyleToken"]:
        """Returns True if this token is an instance of StyleToken."""

        return isinstance(self, StyleToken)

    def is_alias(self) -> TypeGuard["AliasToken"]:
        """Returns True if this token is an instance of AliasToken."""

        return isinstance(self, AliasToken)

    def is_macro(self) -> TypeGuard["MacroToken"]:
        """Returns True if this token is an instance of MacroToken."""

        return isinstance(self, MacroToken)

    def is_clear(self) -> TypeGuard["ClearToken"]:
        """Returns True if this token is an instance of ClearToken."""

        return isinstance(self, ClearToken)

    def is_hyperlink(self) -> TypeGuard["HLinkToken"]:
        """Returns True if this token is an instance of HLinkToken."""

        return isinstance(self, HLinkToken)

    def is_cursor(self) -> TypeGuard["CursorToken"]:
        """Returns True if this token is an instance of CursorToken."""

        return isinstance(self, CursorToken)

markup cached property

Returns markup representing this token.

prettified_markup cached property

Returns syntax-highlighted markup representing this token.

is_alias()

Returns True if this token is an instance of AliasToken.

Source code in pytermgui/markup/tokens.py
92
93
94
95
def is_alias(self) -> TypeGuard["AliasToken"]:
    """Returns True if this token is an instance of AliasToken."""

    return isinstance(self, AliasToken)

is_clear()

Returns True if this token is an instance of ClearToken.

Source code in pytermgui/markup/tokens.py
102
103
104
105
def is_clear(self) -> TypeGuard["ClearToken"]:
    """Returns True if this token is an instance of ClearToken."""

    return isinstance(self, ClearToken)

is_color()

Returns True if this token is an instance of ColorToken.

Source code in pytermgui/markup/tokens.py
82
83
84
85
def is_color(self) -> TypeGuard["ColorToken"]:
    """Returns True if this token is an instance of ColorToken."""

    return isinstance(self, ColorToken)

is_cursor()

Returns True if this token is an instance of CursorToken.

Source code in pytermgui/markup/tokens.py
112
113
114
115
def is_cursor(self) -> TypeGuard["CursorToken"]:
    """Returns True if this token is an instance of CursorToken."""

    return isinstance(self, CursorToken)

Returns True if this token is an instance of HLinkToken.

Source code in pytermgui/markup/tokens.py
107
108
109
110
def is_hyperlink(self) -> TypeGuard["HLinkToken"]:
    """Returns True if this token is an instance of HLinkToken."""

    return isinstance(self, HLinkToken)

is_macro()

Returns True if this token is an instance of MacroToken.

Source code in pytermgui/markup/tokens.py
 97
 98
 99
100
def is_macro(self) -> TypeGuard["MacroToken"]:
    """Returns True if this token is an instance of MacroToken."""

    return isinstance(self, MacroToken)

is_plain()

Returns True if this token is an instance of PlainToken.

Source code in pytermgui/markup/tokens.py
72
73
74
75
def is_plain(self) -> TypeGuard["PlainToken"]:
    """Returns True if this token is an instance of PlainToken."""

    return isinstance(self, PlainToken)

is_pseudo()

Returns True if this token is an instance of PseudoToken.

Source code in pytermgui/markup/tokens.py
77
78
79
80
def is_pseudo(self) -> TypeGuard["PseudoToken"]:
    """Returns True if this token is an instance of PseudoToken."""

    return isinstance(self, PseudoToken)

is_style()

Returns True if this token is an instance of StyleToken.

Source code in pytermgui/markup/tokens.py
87
88
89
90
def is_style(self) -> TypeGuard["StyleToken"]:
    """Returns True if this token is an instance of StyleToken."""

    return isinstance(self, StyleToken)

consume_tag(tag)

Consumes a tag text, returns the associated Token.

Source code in pytermgui/markup/parsing.py
 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
def consume_tag(tag: str) -> Token:  # pylint: disable=too-many-return-statements
    """Consumes a tag text, returns the associated Token."""

    if tag in STYLES:
        return StyleToken(tag)

    if tag.startswith("/"):
        return ClearToken(tag)

    if tag.startswith("!"):
        matchobj = RE_MACRO.match(tag)

        if matchobj is not None:
            name, args = matchobj.groups()

            if args is None:
                return MacroToken(name, tuple())

            return MacroToken(name, tuple(args.split(":")))

    if tag.startswith("~"):
        return HLinkToken(tag[1:])

    if tag.startswith("(") and tag.endswith(")"):
        values = tag[1:-1].split(";")
        if len(values) != 2:
            raise MarkupSyntaxError(
                tag,
                f"should have exactly 2 values separated by `;`, not {len(values)}",
                "",
            )

        return CursorToken(tag[1:-1], *map(int, values))

    if tag in PSEUDO_TOKENS:
        return PseudoToken(tag)

    token: Token
    try:
        token = ColorToken(tag, Color.parse(tag, localize=False))

    except ColorSyntaxError:
        token = AliasToken(tag)

    return token

create_context_dict()

Creates a new context dictionary, initializing its sub-dicts.

Returns:

Type Description
ContextDict

A dictionary with aliases and macros defined as empty sub-dicts.

Source code in pytermgui/markup/parsing.py
83
84
85
86
87
88
89
90
def create_context_dict() -> ContextDict:
    """Creates a new context dictionary, initializing its sub-dicts.

    Returns:
        A dictionary with `aliases` and `macros` defined as empty sub-dicts.
    """

    return {"aliases": {}, "macros": {}}

escape(text)

Escapes any markup found within the given text.

Source code in pytermgui/markup/language.py
41
42
43
44
45
46
47
48
49
def escape(text: str) -> str:
    """Escapes any markup found within the given text."""

    def _repl(matchobj: Match) -> str:
        full, *_ = matchobj.groups()

        return f"\\{full}"

    return RE_MARKUP.sub(_repl, text)

get_markup(text)

Gets the markup representing an ANSI-coded string.

Source code in pytermgui/markup/parsing.py
581
582
583
584
def get_markup(text: str) -> str:
    """Gets the markup representing an ANSI-coded string."""

    return tokens_to_markup(list(tokenize_ansi(text)))

optimize_markup(markup)

Optimizes markup by tokenizing it, optimizing the tokens and converting it back to markup.

Source code in pytermgui/markup/parsing.py
587
588
589
590
def optimize_markup(markup: str) -> str:
    """Optimizes markup by tokenizing it, optimizing the tokens and converting it back to markup."""

    return tokens_to_markup(list(optimize_tokens(list(tokenize_markup(markup)))))

optimize_tokens(tokens)

Optimizes a stream of tokens, only yielding functionally relevant ones.

Parameters:

Name Type Description Default
tokens list[Token]

Any list of Token objects. Usually obtained from tokenize_markup or tokenize_ansi.

required

Yields:

Type Description
Token

All those tokens within the input iterator that are functionally relevant, keeping their order.

Source code in pytermgui/markup/parsing.py
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
def optimize_tokens(tokens: list[Token]) -> Iterator[Token]:
    """Optimizes a stream of tokens, only yielding functionally relevant ones.

    Args:
        tokens: Any list of Token objects. Usually obtained from `tokenize_markup`
            or `tokenize_ansi`.

    Yields:
        All those tokens within the input iterator that are functionally relevant,
            keeping their order.
    """

    previous: list[Token] = []
    current_tag_group: list[Token] = []

    def _diff_previous() -> Iterator[Token]:
        """Find difference from the previously active list of tokens."""

        applied = previous.copy()

        for tkn in current_tag_group:
            targets = []

            clearer = Token.is_clear(tkn)
            if Token.is_clear(tkn):
                targets = [tkn.targets(tag) for tag in applied]

            if tkn in previous and not clearer:
                continue

            if clearer and not any(targets):
                continue

            applied.append(tkn)
            yield tkn

    def _remove_redundant_color(token: Token, new: Color) -> None:
        """Removes non-functional colors.

        These happen in the following ways:
        - Multiple colors of the same channel (fg/bg) are present.
        - A color is applied, then a clearer clears it.
        """

        for applied in current_tag_group.copy():
            if Token.is_clear(applied) and applied.targets(token):
                current_tag_group.remove(applied)

            if not Token.is_color(applied):
                continue

            old = applied.color

            if old.background == new.background:
                current_tag_group.remove(applied)

    for token in tokens:
        if Token.is_plain(token):
            yield from _diff_previous()
            yield token

            previous = current_tag_group.copy()

            continue

        if Token.is_color(token):
            new = token.color

            _remove_redundant_color(token, new)

            if not any(token.markup == applied.markup for applied in current_tag_group):
                current_tag_group.append(token)

            continue

        if token.is_style():
            if not any(token == tag for tag in current_tag_group):
                current_tag_group.append(token)

            continue

        if Token.is_clear(token):
            applied = False
            for tag in current_tag_group.copy():
                if token.targets(tag) or token == tag:
                    current_tag_group.remove(tag)
                    applied = True

            if not applied:
                continue

        current_tag_group.append(token)

    yield from _diff_previous()

parse(text, optimize=False, context=None, append_reset=True, ignore_unknown_tags=True)

Parses markup into the ANSI-coded string it represents.

Parameters:

Name Type Description Default
text str

Any valid markup.

required
optimize bool

If set, optimize_tokens will optimize the tokens found within the input markup before usage. This will incur a (minor) performance hit.

False
context ContextDict | None

The context that aliases and macros found within the markup will be searched in.

None
append_reset bool

If set, [/] will be appended to the token iterator, clearing all styles.

True
ignore_unknown_tags bool

If set, the MarkupSyntaxError coming from unknown tags will be silenced.

True

Returns:

Type Description
str

The ANSI-coded string that the markup represents.

Source code in pytermgui/markup/parsing.py
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
def parse(
    text: str,
    optimize: bool = False,
    context: ContextDict | None = None,
    append_reset: bool = True,
    ignore_unknown_tags: bool = True,
) -> str:
    """Parses markup into the ANSI-coded string it represents.

    Args:
        text: Any valid markup.
        optimize: If set, `optimize_tokens` will optimize the tokens found within the
            input markup before usage. This will incur a (minor) performance hit.
        context: The context that aliases and macros found within the markup will be
            searched in.
        append_reset: If set, `[/]` will be appended to the token iterator, clearing all
            styles.
        ignore_unknown_tags: If set, the `MarkupSyntaxError` coming from unknown tags
            will be silenced.

    Returns:
        The ANSI-coded string that the markup represents.
    """

    if context is None:
        context = create_context_dict()

    if append_reset and not text.endswith("/]"):
        text += "[/]"

    tokens = list(tokenize_markup(text))

    return parse_tokens(
        tokens,
        optimize=optimize,
        context=context,
        append_reset=append_reset,
        ignore_unknown_tags=ignore_unknown_tags,
    )

parse_tokens(tokens, *, optimize=False, context=None, append_reset=True, ignore_unknown_tags=True)

Parses a stream of tokens into the ANSI-coded string they represent.

Parameters:

Name Type Description Default
tokens list[Token]

Any list of Tokens, usually obtained from either tokenize_ansi or tokenize_markup.

required
optimize bool

If set, optimize_tokens will optimize the input iterator before usage. This will incur a (minor) performance hit.

False
context ContextDict | None

The context that aliases and macros found within the tokens will be searched in.

None
append_reset bool

If set, ClearToken("/") will be appended to the token iterator, clearing all styles.

True
ignore_unknown_tags bool

If set, the MarkupSyntaxError coming from unknown tags will be silenced.

True

Returns:

Type Description
str

The ANSI-coded string that the token stream represents.

Source code in pytermgui/markup/parsing.py
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
def parse_tokens(  # pylint: disable=too-many-branches, too-many-locals, too-many-statements
    tokens: list[Token],
    *,
    optimize: bool = False,
    context: ContextDict | None = None,
    append_reset: bool = True,
    ignore_unknown_tags: bool = True,
) -> str:
    """Parses a stream of tokens into the ANSI-coded string they represent.

    Args:
        tokens: Any list of Tokens, usually obtained from either `tokenize_ansi` or
            `tokenize_markup`.
        optimize: If set, `optimize_tokens` will optimize the input iterator before
            usage. This will incur a (minor) performance hit.
        context: The context that aliases and macros found within the tokens will be
            searched in.
        append_reset: If set, `ClearToken("/")` will be appended to the token iterator,
            clearing all styles.
        ignore_unknown_tags: If set, the `MarkupSyntaxError` coming from unknown tags
            will be silenced.

    Returns:
        The ANSI-coded string that the token stream represents.
    """

    if context is None:
        context = create_context_dict()

    token_list = _sub_aliases(tokens, context)

    # It's more computationally efficient to create this lambda once and reuse it
    # every time. There is no need to define a full function, as it just returns
    # a function return.
    get_full = (
        lambda: tokens_to_markup(  # pylint: disable=unnecessary-lambda-assignment
            token_list
        )
    )

    if optimize:
        token_list = list(optimize_tokens(token_list))

    if append_reset:
        token_list.append(ClearToken("/"))

    link = None
    output = ""
    segment = ""
    background = Color.parse("#000000")
    macros: list[MacroToken] = []
    unknown_aliases: list[Token] = []

    save_state: list[Token] = []

    for i, token in enumerate(token_list):
        if token.is_plain():
            value = _apply_macros(
                token.value, (parse_macro(macro, context, get_full) for macro in macros)
            )

            if len(unknown_aliases) > 0:
                output += f"[{' '.join(tkn.value for tkn in unknown_aliases)}]"
                unknown_aliases = []

            output += segment + (
                value if link is None else LINK_TEMPLATE.format(uri=link, label=value)
            )

            segment = ""
            continue

        if token.is_hyperlink():
            link = token.value
            continue

        if Token.is_macro(token):
            macros.append(token)
            continue

        if Token.is_clear(token):
            if token.value in ("/", "/~"):
                link = None

                if token.value == "/~":
                    continue

            found = False
            for macro in macros.copy():
                if token.targets(macro):
                    macros.remove(macro)
                    found = True
                    break

            if found and token.value != "/":
                continue

            if token.value.startswith("/!"):
                raise MarkupSyntaxError(
                    token.value, "has nothing to target", get_full()
                )

        if Token.is_color(token) and token.color.background:
            background = token.color

        if Token.is_pseudo(token):
            if token.value in STATE_PSEUDOS:
                segment += parse_state_pseudo(token, tokens, i, save_state, context)
                continue

            if token.value == "#auto":
                token = ColorToken("#auto", background.contrast)

        try:
            segment += PARSERS[type(token)](token, context, get_full)  # type: ignore

        except MarkupSyntaxError:
            if not ignore_unknown_tags:
                raise

            unknown_aliases.append(token)

    if len(unknown_aliases) > 0:
        output += f"[{' '.join(tkn.value for tkn in unknown_aliases)}]"

    output += segment

    return output

tokenize_ansi(text)

Converts some ANSI-coded text into a stream of tokens.

Parameters:

Name Type Description Default
text str

Any valid ANSI-coded text.

required

Yields:

Type Description
Token

The generated tokens, in the order they occur within the text.

Source code in pytermgui/markup/parsing.py
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
def tokenize_ansi(  # pylint: disable=too-many-locals, too-many-branches, too-many-statements
    text: str,
) -> Iterator[Token]:
    """Converts some ANSI-coded text into a stream of tokens.

    Args:
        text: Any valid ANSI-coded text.

    Yields:
        The generated tokens, in the order they occur within the text.
    """

    cursor = 0

    for matchobj in RE_ANSI.finditer(text):
        start, end = matchobj.span()

        csi = matchobj.groups()[0:2]
        link_osc = matchobj.groups()[2:4]

        if cursor < start:
            yield PlainToken(text[cursor:start])

        if matchobj.groups()[4] is not None:
            cursor = end
            yield ClearToken("/~")
            continue

        if link_osc != (None, None):
            cursor = end
            uri, label = link_osc

            yield HLinkToken(uri)
            yield PlainToken(label)
            yield ClearToken("/~")

            continue

        full, content = csi

        cursor = end

        code = ""

        # Position
        posmatch = RE_POSITION.match(full)

        if posmatch is not None:
            ypos, xpos = posmatch.groups()
            if not ypos and not xpos:
                raise ValueError(
                    f"Cannot parse cursor when no position is supplied. Match: {posmatch!r}"
                )

            yield CursorToken(content, int(ypos) or None, int(xpos) or None)
            continue

        parts = content.split(";")

        state = None
        color_code = ""
        for part in parts:
            if state is None:
                if part in REVERSE_STYLES:
                    yield StyleToken(REVERSE_STYLES[part])
                    continue

                if part in REVERSE_CLEARERS:
                    yield ClearToken(REVERSE_CLEARERS[part])
                    continue

                if part in ("38", "48"):
                    state = "COLOR"
                    color_code += part + ";"
                    continue

                # standard colors
                try:
                    yield ColorToken(part, Color.parse(part, localize=False))
                    continue

                except ColorSyntaxError as exc:
                    raise ValueError(f"Could not parse color tag {part!r}.") from exc

            if state != "COLOR":
                continue

            color_code += part + ";"

            # Ignore incomplete RGB colors
            if (
                color_code.startswith(("38;2;", "48;2;"))
                and len(color_code.split(";")) != 6
            ):
                continue

            try:
                code = color_code

                if code.startswith(("38;2;", "48;2;", "38;5;", "48;5;")):
                    stripped = code[5:-1]

                    if code.startswith("4"):
                        stripped = "@" + stripped

                    code = stripped

                yield ColorToken(code, Color.parse(code, localize=False))

            except ColorSyntaxError:
                continue

            state = None
            color_code = ""

    remaining = text[cursor:]
    if len(remaining) > 0:
        yield PlainToken(remaining)

tokenize_markup(text)

Converts some markup text into a stream of tokens.

Parameters:

Name Type Description Default
text str

Any valid markup.

required

Yields:

Type Description
Token

The generated tokens, in the order they occur within the markup.

Source code in pytermgui/markup/parsing.py
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
def tokenize_markup(text: str) -> Iterator[Token]:
    """Converts some markup text into a stream of tokens.

    Args:
        text: Any valid markup.

    Yields:
        The generated tokens, in the order they occur within the markup.
    """

    cursor = 0
    length = len(text)
    has_inverse = False
    for matchobj in RE_MARKUP.finditer(text):
        full, escapes, content = matchobj.groups()
        start, end = matchobj.span()

        if cursor < start:
            yield PlainToken(text[cursor:start])

        if not escapes == "":
            _, remaining = divmod(len(escapes), 2)

            yield PlainToken(full[max(1 - remaining, 1) :])
            cursor = end

            continue

        for tag in content.split():
            if tag == "inverse":
                has_inverse = True

            if tag == "/inverse":
                has_inverse = False

            consumed = consume_tag(tag)
            if has_inverse:
                if consumed.markup == "/fg":
                    consumed = ClearToken("/fg")

                elif consumed.markup == "/bg":
                    consumed = ClearToken("/bg")

            yield consumed

        cursor = end

    if cursor < length:
        yield PlainToken(text[cursor:length])

tokens_to_markup(tokens)

Converts a token stream into the markup of its tokens.

Parameters:

Name Type Description Default
tokens list[Token]

Any list of Token objects. Usually obtained from tokenize_markup or tokenize_ansi.

required

Returns:

Type Description
str

The markup the given tokens represent.

Source code in pytermgui/markup/parsing.py
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
def tokens_to_markup(tokens: list[Token]) -> str:
    """Converts a token stream into the markup of its tokens.

    Args:
        tokens: Any list of Token objects. Usually obtained from `tokenize_markup` or
            `tokenize_ansi`.

    Returns:
        The markup the given tokens represent.
    """

    tags: list[Token] = []
    markup = ""

    for token in tokens:
        if token.is_plain():
            if len(tags) > 0:
                markup += f"[{' '.join(tag.markup for tag in tags)}]"

            markup += token.value

            tags = []

        else:
            tags.append(token)

    if len(tags) > 0:
        markup += f"[{' '.join(tag.markup for tag in tags)}]"

    return markup