initial import

2023-11-24 08:48:03 -05:00
commit 45f4d6e401
66 changed files with 3601 additions and 0 deletions
@@ -0,0 +1,16 @@
+### Common
+
+Common is a complicated pidgin of influences with multiple regional dialects. Written Common is the language of
+traders, and can be relied upon to be understood by most peoples to a greater or lesser degree.
+
+*Proitsiiiy be itkif eesof detytaen. Ojaot tyskuaz apsoo nirtoet prenao.*
+
+**Common Names:**
+* Rubi Ca Momaman
+* "Quiet" Gushi Murk Lirpusome
+* Fewse Kerloborg
+
+**Noble Common Names:**
+* Lord Pasti Quusi Maghiheim
+* Lady Gotki Lane Lopileigh III
+* Dame Cu Lehaberry IX
@@ -0,0 +1,7 @@
+"""
+Common
+"""
+from .base import Language
+from .names import Name, NobleName
+
+__all__ = [Language, Name, NobleName]
@@ -0,0 +1,158 @@
+from language import types
+
+from .rules import rules
+
+vowels = types.WeightedSet(
+    ("a", 1.0),
+    ("e", 1.0),
+    ("i", 1.0),
+    ("o", 0.8),
+    ("u", 0.7),
+    ("y", 0.01),
+)
+consonants = types.WeightedSet(
+    ("b", 0.5),
+    ("c", 0.5),
+    ("d", 0.5),
+    ("f", 0.3),
+    ("g", 0.3),
+    ("h", 0.5),
+    ("j", 0.2),
+    ("k", 0.3),
+    ("l", 1.0),
+    ("m", 0.5),
+    ("n", 1.0),
+    ("p", 0.5),
+    ("q", 0.05),
+    ("r", 1.0),
+    ("s", 1.0),
+    ("t", 1.0),
+    ("v", 0.3),
+    ("w", 0.2),
+    ("x", 0.2),
+    ("y", 0.01),
+    ("z", 0.1),
+    ("bs", 0.3),
+    ("ct", 0.4),
+    ("ch", 0.4),
+    ("ck", 0.4),
+    ("dd", 0.2),
+    ("ff", 0.2),
+    ("gh", 0.3),
+    ("gs", 0.2),
+    ("ms", 0.4),
+    ("ns", 0.4),
+    ("ps", 0.3),
+    ("qu", 0.2),
+    ("rb", 0.1),
+    ("rd", 0.2),
+    ("rf", 0.1),
+    ("rk", 0.2),
+    ("rl", 0.2),
+    ("rm", 0.2),
+    ("rn", 0.2),
+    ("rp", 0.1),
+    ("rs", 0.75),
+    ("rt", 0.75),
+    ("ry", 0.5),
+    ("sh", 1.0),
+    ("sk", 0.5),
+    ("ss", 0.75),
+    ("st", 1.0),
+    ("sy", 0.5),
+    ("th", 1.0),
+    ("tk", 0.5),
+    ("ts", 1.0),
+    ("tt", 1.0),
+    ("ty", 1.0),
+    ("ws", 0.5),
+)
+
+prefixes = types.equal_weights(["ex", "re", "pre", "de", "pro", "anti"], 0.05)
+
+suffixes = types.equal_weights(
+    [
+        "ad",
+        "ed",
+        "id",
+        "od",
+        "ud",
+        "af",
+        "ef",
+        "if",
+        "of",
+        "uf",
+        "ah",
+        "eh",
+        "ih",
+        "oh",
+        "uh",
+        "al",
+        "el",
+        "il",
+        "ol",
+        "ul",
+        "am",
+        "em",
+        "im",
+        "om",
+        "um",
+        "an",
+        "en",
+        "in",
+        "on",
+        "un",
+        "ar",
+        "er",
+        "ir",
+        "or",
+        "ur",
+        "as",
+        "es",
+        "is",
+        "os",
+        "us",
+        "at",
+        "et",
+        "it",
+        "ot",
+        "ut",
+        "ax",
+        "ex",
+        "ix",
+        "ox",
+        "ux",
+        "ay",
+        "ey",
+        "iy",
+        "oy",
+        "uy",
+        "az",
+        "ez",
+        "iz",
+        "oz",
+        "uz",
+        "ing",
+    ],
+    0.05,
+)
+
+Language = types.Language(
+    name="common",
+    vowels=vowels,
+    consonants=consonants,
+    prefixes=prefixes,
+    suffixes=suffixes,
+    syllables=types.SyllableSet(
+        (types.Syllable(template="vowel|consonant"), 0.01),
+        (types.Syllable(template="vowel|consonant") * 2, 0.2),
+        (types.Syllable(template="vowel|consonant") * 3, 0.4),
+        (types.Syllable(template="vowel|consonant") * 3, 0.5),
+        (types.Syllable(template="vowel|consonant") * 4, 1.0),
+        (types.Syllable(template="vowel|consonant") * 5, 0.3),
+        (types.Syllable(template="vowel|consonant") * 6, 0.2),
+        (types.Syllable(template="vowel|consonant") * 7, 0.05),
+    ),
+    rules=rules,
+    minimum_grapheme_count=1,
+)
@@ -0,0 +1,82 @@
+from language import defaults, types
+from language.languages.common import Language
+
+suffixes = types.equal_weights(
+    [
+        "berg",
+        "borg",
+        "borough",
+        "bury",
+        "berry",
+        "by",
+        "ford",
+        "gard",
+        "grave",
+        "grove",
+        "gren",
+        "hardt",
+        "hart",
+        "heim",
+        "holm",
+        "land",
+        "leigh",
+        "ley",
+        "ly",
+        "lof",
+        "love",
+        "lund",
+        "man",
+        "mark",
+        "ness",
+        "olf",
+        "olph",
+        "quist",
+        "rop",
+        "rup",
+        "stad",
+        "stead",
+        "stein",
+        "strom",
+        "thal",
+        "thorpe",
+        "ton",
+        "vall",
+        "wich",
+        "win",
+        "some",
+        "smith",
+        "bridge",
+        "cope",
+        "town",
+        "er",
+        "don",
+        "den",
+        "dell",
+        "son",
+    ]
+)
+
+Name = types.NameGenerator(
+    language=Language,
+    syllables=types.SyllableSet(
+        (types.Syllable(template="vowel|consonant"), 0.01),
+        (types.Syllable(template="consonant,vowel"), 0.2),
+        (types.Syllable(template="consonant,vowel") * 2, 1.0),
+    ),
+    templates=types.NameSet(
+        (types.NameTemplate("adjective,title,name,surname,count"), 1.0),
+        (types.NameTemplate("title,name,name,surname,count"), 1.0),
+        (types.NameTemplate("title,name,name,surname,surname,count"), 1.0),
+    ),
+    names=None,
+    surnames=None,
+    nicknames=None,
+    adjectives=defaults.adjectives,
+    titles=defaults.titles,
+    counts=defaults.counts,
+    suffixes=suffixes,
+)
+Name.language.prefixes = None
+Name.language.suffixes = None
+
+NobleName = Name
@@ -0,0 +1,115 @@
+import logging
+import re
+
+from language.rules import default_rules
+from language.types import Language
+
+logger = logging.getLogger()
+
+permitted_starting_clusters = [
+    "bh",
+    "bl",
+    "br",
+    "bw",
+    "by",
+    "ch",
+    "cl",
+    "cr",
+    "cw",
+    "cy",
+    "dh",
+    "dj",
+    "dr",
+    "dw",
+    "dy",
+    "fl",
+    "fn",
+    "fr",
+    "fw",
+    "fy",
+    "gh",
+    "gl",
+    "gn",
+    "gr",
+    "gw",
+    "gy",
+    "hy",
+    "jh",
+    "jy",
+    "kh",
+    "kl",
+    "kr",
+    "kw",
+    "ky",
+    "ll",
+    "ly",
+    "mw",
+    "my",
+    "ny",
+    "ph",
+    "pl",
+    "pn",
+    "pr",
+    "pw",
+    "py",
+    "rh",
+    "ry",
+    "sb",
+    "sc",
+    "sd",
+    "sf",
+    "sg",
+    "sh",
+    "sj",
+    "sk",
+    "sl",
+    "sm",
+    "sn",
+    "sp",
+    "sr",
+    "st",
+    "sv",
+    "sw",
+    "sy",
+    "th",
+    "tr",
+    "tw",
+    "ty",
+    "vy",
+    "wh",
+    "wr",
+    "wy",
+    "xh",
+    "xy",
+    "yh",
+    "zb",
+    "zc",
+    "zd",
+    "zh",
+    "zl",
+    "zm",
+    "zn",
+    "zr",
+    "zw",
+    "zy",
+]
+
+
+def cannot_start_with_two_consonants(language: Language, word: str) -> bool:
+    found = re.compile(r"(^[bcdfghjklmnpqrstvwxz]{2})").search(word)
+    if not found:
+        return True
+    first, second = found.group(1)
+
+    if first == second:
+        logger.debug(f"{word} starts with a repeated consonant.")
+        return False
+
+    return found in permitted_starting_clusters
+
+
+rules = default_rules.union(
+    {
+        cannot_start_with_two_consonants,
+    }
+)