@pairling/runtime-darwin-x64 0.1.0 → 0.2.0

package/python/lib/python3.12/re/__init__.py

@@ -0,0 +1,385 @@
+#
+# Secret Labs' Regular Expression Engine
+#
+# re-compatible interface for the sre matching engine
+#
+# Copyright (c) 1998-2001 by Secret Labs AB.  All rights reserved.
+#
+# This version of the SRE library can be redistributed under CNRI's
+# Python 1.6 license.  For any other use, please contact Secret Labs
+# AB (info@pythonware.com).
+#
+# Portions of this engine have been developed in cooperation with
+# CNRI.  Hewlett-Packard provided funding for 1.6 integration and
+# other compatibility work.
+#
+
+r"""Support for regular expressions (RE).
+
+This module provides regular expression matching operations similar to
+those found in Perl.  It supports both 8-bit and Unicode strings; both
+the pattern and the strings being processed can contain null bytes and
+characters outside the US ASCII range.
+
+Regular expressions can contain both special and ordinary characters.
+Most ordinary characters, like "A", "a", or "0", are the simplest
+regular expressions; they simply match themselves.  You can
+concatenate ordinary characters, so last matches the string 'last'.
+
+The special characters are:
+    "."      Matches any character except a newline.
+    "^"      Matches the start of the string.
+    "$"      Matches the end of the string or just before the newline at
+             the end of the string.
+    "*"      Matches 0 or more (greedy) repetitions of the preceding RE.
+             Greedy means that it will match as many repetitions as possible.
+    "+"      Matches 1 or more (greedy) repetitions of the preceding RE.
+    "?"      Matches 0 or 1 (greedy) of the preceding RE.
+    *?,+?,?? Non-greedy versions of the previous three special characters.
+    {m,n}    Matches from m to n repetitions of the preceding RE.
+    {m,n}?   Non-greedy version of the above.
+    "\\"     Either escapes special characters or signals a special sequence.
+    []       Indicates a set of characters.
+             A "^" as the first character indicates a complementing set.
+    "|"      A|B, creates an RE that will match either A or B.
+    (...)    Matches the RE inside the parentheses.
+             The contents can be retrieved or matched later in the string.
+    (?aiLmsux) The letters set the corresponding flags defined below.
+    (?:...)  Non-grouping version of regular parentheses.
+    (?P<name>...) The substring matched by the group is accessible by name.
+    (?P=name)     Matches the text matched earlier by the group named name.
+    (?#...)  A comment; ignored.
+    (?=...)  Matches if ... matches next, but doesn't consume the string.
+    (?!...)  Matches if ... doesn't match next.
+    (?<=...) Matches if preceded by ... (must be fixed length).
+    (?<!...) Matches if not preceded by ... (must be fixed length).
+    (?(id/name)yes|no) Matches yes pattern if the group with id/name matched,
+                       the (optional) no pattern otherwise.
+
+The special sequences consist of "\\" and a character from the list
+below.  If the ordinary character is not on the list, then the
+resulting RE will match the second character.
+    \number  Matches the contents of the group of the same number.
+    \A       Matches only at the start of the string.
+    \Z       Matches only at the end of the string.
+    \b       Matches the empty string, but only at the start or end of a word.
+    \B       Matches the empty string, but not at the start or end of a word.
+    \d       Matches any decimal digit; equivalent to the set [0-9] in
+             bytes patterns or string patterns with the ASCII flag.
+             In string patterns without the ASCII flag, it will match the whole
+             range of Unicode digits.
+    \D       Matches any non-digit character; equivalent to [^\d].
+    \s       Matches any whitespace character; equivalent to [ \t\n\r\f\v] in
+             bytes patterns or string patterns with the ASCII flag.
+             In string patterns without the ASCII flag, it will match the whole
+             range of Unicode whitespace characters.
+    \S       Matches any non-whitespace character; equivalent to [^\s].
+    \w       Matches any alphanumeric character; equivalent to [a-zA-Z0-9_]
+             in bytes patterns or string patterns with the ASCII flag.
+             In string patterns without the ASCII flag, it will match the
+             range of Unicode alphanumeric characters (letters plus digits
+             plus underscore).
+             With LOCALE, it will match the set [0-9_] plus characters defined
+             as letters for the current locale.
+    \W       Matches the complement of \w.
+    \\       Matches a literal backslash.
+
+This module exports the following functions:
+    match     Match a regular expression pattern to the beginning of a string.
+    fullmatch Match a regular expression pattern to all of a string.
+    search    Search a string for the presence of a pattern.
+    sub       Substitute occurrences of a pattern found in a string.
+    subn      Same as sub, but also return the number of substitutions made.
+    split     Split a string by the occurrences of a pattern.
+    findall   Find all occurrences of a pattern in a string.
+    finditer  Return an iterator yielding a Match object for each match.
+    compile   Compile a pattern into a Pattern object.
+    purge     Clear the regular expression cache.
+    escape    Backslash all non-alphanumerics in a string.
+
+Each function other than purge and escape can take an optional 'flags' argument
+consisting of one or more of the following module constants, joined by "|".
+A, L, and U are mutually exclusive.
+    A  ASCII       For string patterns, make \w, \W, \b, \B, \d, \D
+                   match the corresponding ASCII character categories
+                   (rather than the whole Unicode categories, which is the
+                   default).
+                   For bytes patterns, this flag is the only available
+                   behaviour and needn't be specified.
+    I  IGNORECASE  Perform case-insensitive matching.
+    L  LOCALE      Make \w, \W, \b, \B, dependent on the current locale.
+    M  MULTILINE   "^" matches the beginning of lines (after a newline)
+                   as well as the string.
+                   "$" matches the end of lines (before a newline) as well
+                   as the end of the string.
+    S  DOTALL      "." matches any character at all, including the newline.
+    X  VERBOSE     Ignore whitespace and comments for nicer looking RE's.
+    U  UNICODE     For compatibility only. Ignored for string patterns (it
+                   is the default), and forbidden for bytes patterns.
+
+This module also defines an exception 'error'.
+
+"""
+
+import enum
+from . import _compiler, _parser
+import functools
+import _sre
+
+
+# public symbols
+__all__ = [
+    "match", "fullmatch", "search", "sub", "subn", "split",
+    "findall", "finditer", "compile", "purge", "template", "escape",
+    "error", "Pattern", "Match", "A", "I", "L", "M", "S", "X", "U",
+    "ASCII", "IGNORECASE", "LOCALE", "MULTILINE", "DOTALL", "VERBOSE",
+    "UNICODE", "NOFLAG", "RegexFlag",
+]
+
+__version__ = "2.2.1"
+
+@enum.global_enum
+@enum._simple_enum(enum.IntFlag, boundary=enum.KEEP)
+class RegexFlag:
+    NOFLAG = 0
+    ASCII = A = _compiler.SRE_FLAG_ASCII # assume ascii "locale"
+    IGNORECASE = I = _compiler.SRE_FLAG_IGNORECASE # ignore case
+    LOCALE = L = _compiler.SRE_FLAG_LOCALE # assume current 8-bit locale
+    UNICODE = U = _compiler.SRE_FLAG_UNICODE # assume unicode "locale"
+    MULTILINE = M = _compiler.SRE_FLAG_MULTILINE # make anchors look for newline
+    DOTALL = S = _compiler.SRE_FLAG_DOTALL # make dot match newline
+    VERBOSE = X = _compiler.SRE_FLAG_VERBOSE # ignore whitespace and comments
+    # sre extensions (experimental, don't rely on these)
+    TEMPLATE = T = _compiler.SRE_FLAG_TEMPLATE # unknown purpose, deprecated
+    DEBUG = _compiler.SRE_FLAG_DEBUG # dump pattern after compilation
+    __str__ = object.__str__
+    _numeric_repr_ = hex
+
+# sre exception
+error = _compiler.error
+
+# --------------------------------------------------------------------
+# public interface
+
+def match(pattern, string, flags=0):
+    """Try to apply the pattern at the start of the string, returning
+    a Match object, or None if no match was found."""
+    return _compile(pattern, flags).match(string)
+
+def fullmatch(pattern, string, flags=0):
+    """Try to apply the pattern to all of the string, returning
+    a Match object, or None if no match was found."""
+    return _compile(pattern, flags).fullmatch(string)
+
+def search(pattern, string, flags=0):
+    """Scan through string looking for a match to the pattern, returning
+    a Match object, or None if no match was found."""
+    return _compile(pattern, flags).search(string)
+
+def sub(pattern, repl, string, count=0, flags=0):
+    """Return the string obtained by replacing the leftmost
+    non-overlapping occurrences of the pattern in string by the
+    replacement repl.  repl can be either a string or a callable;
+    if a string, backslash escapes in it are processed.  If it is
+    a callable, it's passed the Match object and must return
+    a replacement string to be used."""
+    return _compile(pattern, flags).sub(repl, string, count)
+
+def subn(pattern, repl, string, count=0, flags=0):
+    """Return a 2-tuple containing (new_string, number).
+    new_string is the string obtained by replacing the leftmost
+    non-overlapping occurrences of the pattern in the source
+    string by the replacement repl.  number is the number of
+    substitutions that were made. repl can be either a string or a
+    callable; if a string, backslash escapes in it are processed.
+    If it is a callable, it's passed the Match object and must
+    return a replacement string to be used."""
+    return _compile(pattern, flags).subn(repl, string, count)
+
+def split(pattern, string, maxsplit=0, flags=0):
+    """Split the source string by the occurrences of the pattern,
+    returning a list containing the resulting substrings.  If
+    capturing parentheses are used in pattern, then the text of all
+    groups in the pattern are also returned as part of the resulting
+    list.  If maxsplit is nonzero, at most maxsplit splits occur,
+    and the remainder of the string is returned as the final element
+    of the list."""
+    return _compile(pattern, flags).split(string, maxsplit)
+
+def findall(pattern, string, flags=0):
+    """Return a list of all non-overlapping matches in the string.
+
+    If one or more capturing groups are present in the pattern, return
+    a list of groups; this will be a list of tuples if the pattern
+    has more than one group.
+
+    Empty matches are included in the result."""
+    return _compile(pattern, flags).findall(string)
+
+def finditer(pattern, string, flags=0):
+    """Return an iterator over all non-overlapping matches in the
+    string.  For each match, the iterator returns a Match object.
+
+    Empty matches are included in the result."""
+    return _compile(pattern, flags).finditer(string)
+
+def compile(pattern, flags=0):
+    "Compile a regular expression pattern, returning a Pattern object."
+    return _compile(pattern, flags)
+
+def purge():
+    "Clear the regular expression caches"
+    _cache.clear()
+    _cache2.clear()
+    _compile_template.cache_clear()
+
+def template(pattern, flags=0):
+    "Compile a template pattern, returning a Pattern object, deprecated"
+    import warnings
+    warnings.warn("The re.template() function is deprecated "
+                  "as it is an undocumented function "
+                  "without an obvious purpose. "
+                  "Use re.compile() instead.",
+                  DeprecationWarning)
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore", DeprecationWarning)  # warn just once
+        return _compile(pattern, flags|T)
+
+# SPECIAL_CHARS
+# closing ')', '}' and ']'
+# '-' (a range in character set)
+# '&', '~', (extended character set operations)
+# '#' (comment) and WHITESPACE (ignored) in verbose mode
+_special_chars_map = {i: '\\' + chr(i) for i in b'()[]{}?*+-|^$\\.&~# \t\n\r\v\f'}
+
+def escape(pattern):
+    """
+    Escape special characters in a string.
+    """
+    if isinstance(pattern, str):
+        return pattern.translate(_special_chars_map)
+    else:
+        pattern = str(pattern, 'latin1')
+        return pattern.translate(_special_chars_map).encode('latin1')
+
+Pattern = type(_compiler.compile('', 0))
+Match = type(_compiler.compile('', 0).match(''))
+
+# --------------------------------------------------------------------
+# internals
+
+# Use the fact that dict keeps the insertion order.
+# _cache2 uses the simple FIFO policy which has better latency.
+# _cache uses the LRU policy which has better hit rate.
+_cache = {}  # LRU
+_cache2 = {}  # FIFO
+_MAXCACHE = 512
+_MAXCACHE2 = 256
+assert _MAXCACHE2 < _MAXCACHE
+
+def _compile(pattern, flags):
+    # internal: compile pattern
+    if isinstance(flags, RegexFlag):
+        flags = flags.value
+    try:
+        return _cache2[type(pattern), pattern, flags]
+    except KeyError:
+        pass
+
+    key = (type(pattern), pattern, flags)
+    # Item in _cache should be moved to the end if found.
+    p = _cache.pop(key, None)
+    if p is None:
+        if isinstance(pattern, Pattern):
+            if flags:
+                raise ValueError(
+                    "cannot process flags argument with a compiled pattern")
+            return pattern
+        if not _compiler.isstring(pattern):
+            raise TypeError("first argument must be string or compiled pattern")
+        if flags & T:
+            import warnings
+            warnings.warn("The re.TEMPLATE/re.T flag is deprecated "
+                    "as it is an undocumented flag "
+                    "without an obvious purpose. "
+                    "Don't use it.",
+                    DeprecationWarning)
+        p = _compiler.compile(pattern, flags)
+        if flags & DEBUG:
+            return p
+        if len(_cache) >= _MAXCACHE:
+            # Drop the least recently used item.
+            # next(iter(_cache)) is known to have linear amortized time,
+            # but it is used here to avoid a dependency from using OrderedDict.
+            # For the small _MAXCACHE value it doesn't make much of a difference.
+            try:
+                del _cache[next(iter(_cache))]
+            except (StopIteration, RuntimeError, KeyError):
+                pass
+    # Append to the end.
+    _cache[key] = p
+
+    if len(_cache2) >= _MAXCACHE2:
+        # Drop the oldest item.
+        try:
+            del _cache2[next(iter(_cache2))]
+        except (StopIteration, RuntimeError, KeyError):
+            pass
+    _cache2[key] = p
+    return p
+
+@functools.lru_cache(_MAXCACHE)
+def _compile_template(pattern, repl):
+    # internal: compile replacement pattern
+    return _sre.template(pattern, _parser.parse_template(repl, pattern))
+
+# register myself for pickling
+
+import copyreg
+
+def _pickle(p):
+    return _compile, (p.pattern, p.flags)
+
+copyreg.pickle(Pattern, _pickle, _compile)
+
+# --------------------------------------------------------------------
+# experimental stuff (see python-dev discussions for details)
+
+class Scanner:
+    def __init__(self, lexicon, flags=0):
+        from ._constants import BRANCH, SUBPATTERN
+        if isinstance(flags, RegexFlag):
+            flags = flags.value
+        self.lexicon = lexicon
+        # combine phrases into a compound pattern
+        p = []
+        s = _parser.State()
+        s.flags = flags
+        for phrase, action in lexicon:
+            gid = s.opengroup()
+            p.append(_parser.SubPattern(s, [
+                (SUBPATTERN, (gid, 0, 0, _parser.parse(phrase, flags))),
+                ]))
+            s.closegroup(gid, p[-1])
+        p = _parser.SubPattern(s, [(BRANCH, (None, p))])
+        self.scanner = _compiler.compile(p)
+    def scan(self, string):
+        result = []
+        append = result.append
+        match = self.scanner.scanner(string).match
+        i = 0
+        while True:
+            m = match()
+            if not m:
+                break
+            j = m.end()
+            if i == j:
+                break
+            action = self.lexicon[m.lastindex-1][1]
+            if callable(action):
+                self.match = m
+                action = action(self, m.group())
+            if action is not None:
+                append(action)
+            i = j
+        return result, string[i:]

package/python/lib/python3.12/re/_casefix.py

@@ -0,0 +1,106 @@
+# Auto-generated by Tools/build/generate_re_casefix.py.
+
+# Maps the code of lowercased character to codes of different lowercased
+# characters which have the same uppercase.
+_EXTRA_CASES = {
+    # LATIN SMALL LETTER I: LATIN SMALL LETTER DOTLESS I
+    0x0069: (0x0131,), # 'i': 'ı'
+    # LATIN SMALL LETTER S: LATIN SMALL LETTER LONG S
+    0x0073: (0x017f,), # 's': 'ſ'
+    # MICRO SIGN: GREEK SMALL LETTER MU
+    0x00b5: (0x03bc,), # 'µ': 'μ'
+    # LATIN SMALL LETTER DOTLESS I: LATIN SMALL LETTER I
+    0x0131: (0x0069,), # 'ı': 'i'
+    # LATIN SMALL LETTER LONG S: LATIN SMALL LETTER S
+    0x017f: (0x0073,), # 'ſ': 's'
+    # COMBINING GREEK YPOGEGRAMMENI: GREEK SMALL LETTER IOTA, GREEK PROSGEGRAMMENI
+    0x0345: (0x03b9, 0x1fbe), # '\u0345': 'ιι'
+    # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS: GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
+    0x0390: (0x1fd3,), # 'ΐ': 'ΐ'
+    # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS: GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
+    0x03b0: (0x1fe3,), # 'ΰ': 'ΰ'
+    # GREEK SMALL LETTER BETA: GREEK BETA SYMBOL
+    0x03b2: (0x03d0,), # 'β': 'ϐ'
+    # GREEK SMALL LETTER EPSILON: GREEK LUNATE EPSILON SYMBOL
+    0x03b5: (0x03f5,), # 'ε': 'ϵ'
+    # GREEK SMALL LETTER THETA: GREEK THETA SYMBOL
+    0x03b8: (0x03d1,), # 'θ': 'ϑ'
+    # GREEK SMALL LETTER IOTA: COMBINING GREEK YPOGEGRAMMENI, GREEK PROSGEGRAMMENI
+    0x03b9: (0x0345, 0x1fbe), # 'ι': '\u0345ι'
+    # GREEK SMALL LETTER KAPPA: GREEK KAPPA SYMBOL
+    0x03ba: (0x03f0,), # 'κ': 'ϰ'
+    # GREEK SMALL LETTER MU: MICRO SIGN
+    0x03bc: (0x00b5,), # 'μ': 'µ'
+    # GREEK SMALL LETTER PI: GREEK PI SYMBOL
+    0x03c0: (0x03d6,), # 'π': 'ϖ'
+    # GREEK SMALL LETTER RHO: GREEK RHO SYMBOL
+    0x03c1: (0x03f1,), # 'ρ': 'ϱ'
+    # GREEK SMALL LETTER FINAL SIGMA: GREEK SMALL LETTER SIGMA
+    0x03c2: (0x03c3,), # 'ς': 'σ'
+    # GREEK SMALL LETTER SIGMA: GREEK SMALL LETTER FINAL SIGMA
+    0x03c3: (0x03c2,), # 'σ': 'ς'
+    # GREEK SMALL LETTER PHI: GREEK PHI SYMBOL
+    0x03c6: (0x03d5,), # 'φ': 'ϕ'
+    # GREEK BETA SYMBOL: GREEK SMALL LETTER BETA
+    0x03d0: (0x03b2,), # 'ϐ': 'β'
+    # GREEK THETA SYMBOL: GREEK SMALL LETTER THETA
+    0x03d1: (0x03b8,), # 'ϑ': 'θ'
+    # GREEK PHI SYMBOL: GREEK SMALL LETTER PHI
+    0x03d5: (0x03c6,), # 'ϕ': 'φ'
+    # GREEK PI SYMBOL: GREEK SMALL LETTER PI
+    0x03d6: (0x03c0,), # 'ϖ': 'π'
+    # GREEK KAPPA SYMBOL: GREEK SMALL LETTER KAPPA
+    0x03f0: (0x03ba,), # 'ϰ': 'κ'
+    # GREEK RHO SYMBOL: GREEK SMALL LETTER RHO
+    0x03f1: (0x03c1,), # 'ϱ': 'ρ'
+    # GREEK LUNATE EPSILON SYMBOL: GREEK SMALL LETTER EPSILON
+    0x03f5: (0x03b5,), # 'ϵ': 'ε'
+    # CYRILLIC SMALL LETTER VE: CYRILLIC SMALL LETTER ROUNDED VE
+    0x0432: (0x1c80,), # 'в': 'ᲀ'
+    # CYRILLIC SMALL LETTER DE: CYRILLIC SMALL LETTER LONG-LEGGED DE
+    0x0434: (0x1c81,), # 'д': 'ᲁ'
+    # CYRILLIC SMALL LETTER O: CYRILLIC SMALL LETTER NARROW O
+    0x043e: (0x1c82,), # 'о': 'ᲂ'
+    # CYRILLIC SMALL LETTER ES: CYRILLIC SMALL LETTER WIDE ES
+    0x0441: (0x1c83,), # 'с': 'ᲃ'
+    # CYRILLIC SMALL LETTER TE: CYRILLIC SMALL LETTER TALL TE, CYRILLIC SMALL LETTER THREE-LEGGED TE
+    0x0442: (0x1c84, 0x1c85), # 'т': 'ᲄᲅ'
+    # CYRILLIC SMALL LETTER HARD SIGN: CYRILLIC SMALL LETTER TALL HARD SIGN
+    0x044a: (0x1c86,), # 'ъ': 'ᲆ'
+    # CYRILLIC SMALL LETTER YAT: CYRILLIC SMALL LETTER TALL YAT
+    0x0463: (0x1c87,), # 'ѣ': 'ᲇ'
+    # CYRILLIC SMALL LETTER ROUNDED VE: CYRILLIC SMALL LETTER VE
+    0x1c80: (0x0432,), # 'ᲀ': 'в'
+    # CYRILLIC SMALL LETTER LONG-LEGGED DE: CYRILLIC SMALL LETTER DE
+    0x1c81: (0x0434,), # 'ᲁ': 'д'
+    # CYRILLIC SMALL LETTER NARROW O: CYRILLIC SMALL LETTER O
+    0x1c82: (0x043e,), # 'ᲂ': 'о'
+    # CYRILLIC SMALL LETTER WIDE ES: CYRILLIC SMALL LETTER ES
+    0x1c83: (0x0441,), # 'ᲃ': 'с'
+    # CYRILLIC SMALL LETTER TALL TE: CYRILLIC SMALL LETTER TE, CYRILLIC SMALL LETTER THREE-LEGGED TE
+    0x1c84: (0x0442, 0x1c85), # 'ᲄ': 'тᲅ'
+    # CYRILLIC SMALL LETTER THREE-LEGGED TE: CYRILLIC SMALL LETTER TE, CYRILLIC SMALL LETTER TALL TE
+    0x1c85: (0x0442, 0x1c84), # 'ᲅ': 'тᲄ'
+    # CYRILLIC SMALL LETTER TALL HARD SIGN: CYRILLIC SMALL LETTER HARD SIGN
+    0x1c86: (0x044a,), # 'ᲆ': 'ъ'
+    # CYRILLIC SMALL LETTER TALL YAT: CYRILLIC SMALL LETTER YAT
+    0x1c87: (0x0463,), # 'ᲇ': 'ѣ'
+    # CYRILLIC SMALL LETTER UNBLENDED UK: CYRILLIC SMALL LETTER MONOGRAPH UK
+    0x1c88: (0xa64b,), # 'ᲈ': 'ꙋ'
+    # LATIN SMALL LETTER S WITH DOT ABOVE: LATIN SMALL LETTER LONG S WITH DOT ABOVE
+    0x1e61: (0x1e9b,), # 'ṡ': 'ẛ'
+    # LATIN SMALL LETTER LONG S WITH DOT ABOVE: LATIN SMALL LETTER S WITH DOT ABOVE
+    0x1e9b: (0x1e61,), # 'ẛ': 'ṡ'
+    # GREEK PROSGEGRAMMENI: COMBINING GREEK YPOGEGRAMMENI, GREEK SMALL LETTER IOTA
+    0x1fbe: (0x0345, 0x03b9), # 'ι': '\u0345ι'
+    # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA: GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
+    0x1fd3: (0x0390,), # 'ΐ': 'ΐ'
+    # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA: GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
+    0x1fe3: (0x03b0,), # 'ΰ': 'ΰ'
+    # CYRILLIC SMALL LETTER MONOGRAPH UK: CYRILLIC SMALL LETTER UNBLENDED UK
+    0xa64b: (0x1c88,), # 'ꙋ': 'ᲈ'
+    # LATIN SMALL LIGATURE LONG S T: LATIN SMALL LIGATURE ST
+    0xfb05: (0xfb06,), # 'ſt': 'st'
+    # LATIN SMALL LIGATURE ST: LATIN SMALL LIGATURE LONG S T
+    0xfb06: (0xfb05,), # 'st': 'ſt'
+}