We want to map readings and graphemes in cuneiform corpora to cuneiform unicode characters, based on extant mapping tables.
We generate a plain mapping that can be used readily by programs that convert from ATF to TF or something else.
There are multiple mapping tables, there are several ways to transliterate readings.
We take the ATF transliterations from CDLI, for tablets of various corpora.
We take the file GeneratedSignList.json with mappings like
"BANIA": {
"signName": "BANIA",
"signNumber": 551,
"signCunei": "𒑔",
"codePoint": "",
"values":
[
"BANIA", "AŠ2.UoverU", "5SŪTU"
]
},
"MA": {
"signName": "MA",
"signNumber": 552,
"signCunei": "𒈠",
"codePoint": "",
"values":
[
"MA", "PEŠ3", "PEŠŠE", "WA6"
]
},
See transcription about the provenance of this file.
This is work in progress. The mapping is needed in the conversion from ATF to TF in the program tfFromATF.py.
Cale Johnson, Martijn Kokken, Dirk Roorda
We are indebted to Auday Hussein for helpfully sending GeneratedSignList.json file to us; to Alba de Ridder for hints and comments.
import os
import collections
import json
from unicodedata import name as uname
BASE = os.path.expanduser("~/github")
ORG = "Nino-cunei"
REPO = "signs"
REPO_DIR = f"{BASE}/{ORG}/{REPO}"
WRITING_DIR = f"{REPO_DIR}/writing"
SIGN_FILE = "GeneratedSignList.json"
SIGN_PATH = f"{WRITING_DIR}/{SIGN_FILE}"
MAPPING_FILE = f'{os.path.abspath("..")}/characters/mapping.tsv'
AMBI_FILE = f'{os.path.abspath("..")}/characters/ambiguous.tsv'
We read sign files for various corpora.
CORPORA = """
oldbabylonian
oldassyrian
""".strip().split()
charFiles = {corp: f"{BASE}/{ORG}/{corp}/characters/corpus.tsv" for corp in CORPORA}
tokens = set()
for (corp, charFile) in charFiles.items():
with open(charFile) as f:
theseTokens = set()
for line in f:
(repeat, sign) = line.rstrip("\n").split("\t")
theseTokens.add((repeat, sign) if repeat else sign)
print(f"{corp:<15}: {len(theseTokens)} readings")
tokens |= theseTokens
print(f'{"TOTAL":<15}: {len(tokens)} readings')
oldbabylonian : 976 readings oldassyrian : 639 readings TOTAL : 1145 readings
We use mappings between Unicode style transliterations and ATF.
transAscii = {
"š": "sz",
"ṣ": "s,",
"ś": "s'",
"ṭ": "t,",
"ḫ": "h,",
}
transAscii.update({k.upper(): v.upper() for (k, v) in transAscii.items()})
def makeAscii(r):
for (rin, rout) in transAscii.items():
r = r.replace(rin, rout)
return r
transAscii
{'š': 'sz',
'ṣ': 's,',
'ś': "s'",
'ṭ': 't,',
'ḫ': 'h,',
'Š': 'SZ',
'Ṣ': 'S,',
'Ś': "S'",
'Ṭ': 'T,',
'Ḫ': 'H,'}
REPEAT_INV = dict(
one=1,
two=2,
three=3,
four=4,
five=5,
six=6,
seven=7,
eight=8,
nine=9,
)
REPEAT = {v: k for (k, v) in REPEAT_INV.items()}
FRACTION = {
"1/2": "one half",
"1/3": "one third",
"2/3": "two thirds",
"1/4": "one quarter",
"1/6": "one sixth",
"5/6": "five sixths",
"1/8": "one eighth",
}
We read the json file with generated signs.
For each sign, we find a list of values.
These values correspond to possible readings or graphemes, in short, tokens. They are in unicode transliteration style.
In the mapping we create, we convert them to plain ATF, which makes it easier to look them up from our Old Babylonian corpus.
with open(SIGN_PATH) as fh:
signs = json.load(fh)["signs"]
print(f"{len(signs)} signs in the json file")
mapping = collections.defaultdict(set)
for (sign, signData) in signs.items():
uniStr = signData["signCunei"]
values = signData["values"]
for value in values:
valueAscii = makeAscii(value)
mapping[valueAscii].add(uniStr)
print(f"{len(mapping)} distinct values in table")
1768 signs in the json file 8765 distinct values in table
We look up each corpus token in the mapping just constructed.
Depending on whether we find 0, 1 or multiple values, we store them in dictionaries
unmapped, unique, multiple.
MAPPING_FIXES = {
"d": "dingir",
}
unmapped = set()
unique = {}
multiple = {}
for t in tokens:
if type(t) is tuple:
unmapped.add(t)
continue
tLookup = MAPPING_FIXES.get(t, t)
tU = tLookup.upper()
if tU not in mapping:
unmapped.add(t)
continue
targets = mapping[tU]
if len(targets) == 1:
unique[t] = list(targets)[0]
else:
multiple[t] = targets
print(f"{len(unmapped):>3} unmapped tokens")
print(f"{len(multiple):>3} ambiguously mapped tokens")
print(f"{len(unique):>3} uniquely mapped tokens")
182 unmapped tokens 58 ambiguously mapped tokens 905 uniquely mapped tokens
MAPPING_FIXES = {
"d": "dingir",
}
unmapped = set()
unique = {}
multiple = {}
for t in tokens:
if type(t) is tuple:
unmapped.add(t)
continue
tLookup = MAPPING_FIXES.get(t, t)
tU = tLookup.upper()
if tU not in mapping:
unmapped.add(t)
continue
targets = mapping[tU]
if len(targets) == 1:
unique[t] = list(targets)[0]
else:
multiple[t] = targets
print(f"{len(unmapped):>3} unmapped tokens")
print(f"{len(multiple):>3} ambiguously mapped tokens")
print(f"{len(unique):>3} uniquely mapped tokens")
182 unmapped tokens 58 ambiguously mapped tokens 905 uniquely mapped tokens
def unkey(x):
return (x[1].lower(), str(x[0])) if type(x) is tuple else (x.lower(), "")
print(f"{len(unmapped):>3} unmapped tokens")
sorted(unmapped, key=unkey)
182 unmapped tokens
['&i2',
"'i",
'...',
'2(disz@t)',
"a'",
'ah',
'AH',
'alamusz',
'asal2',
('1', 'asz'),
('1/2', 'asz'),
('1/3', 'asz'),
('2', 'asz'),
('3', 'asz'),
('4', 'asz'),
('5', 'asz'),
('6', 'asz'),
('7', 'asz'),
('8', 'asz'),
('9', 'asz'),
'babila',
'babila2',
('1', 'ban2'),
('2', 'ban2'),
('3', 'ban2'),
('4', 'ban2'),
('5', 'ban2'),
'barig',
('1', 'barig'),
('2', 'barig'),
('3', 'barig'),
('4', 'barig'),
('5', 'barig'),
"bur'u",
('1', "bur'u"),
('2', "bur'u"),
('3', "bur'u"),
('4', "bur'u"),
('5', "bur'u"),
('1', 'bur3'),
('2', 'bur3'),
('3', 'bur3'),
('4', 'bur3'),
('5', 'bur3'),
('6', 'bur3'),
('8', 'bur3'),
('9', 'bur3'),
'dah',
('1', 'disz'),
('1/2', 'disz'),
('1/3', 'disz'),
('1/4', 'disz'),
('1/6', 'disz'),
('2', 'disz'),
('2/2', 'disz'),
('2/3', 'disz'),
('3', 'disz'),
('3/4', 'disz'),
('4', 'disz'),
('5', 'disz'),
('5/6', 'disz'),
('6', 'disz'),
('7', 'disz'),
('8', 'disz'),
('9', 'disz'),
'duh',
'eh',
'EH',
'eri11',
('1', 'esze3'),
('2', 'esze3'),
('3', 'esze3'),
('1', 'gesz'),
('9', 'gesz'),
"gesz'u",
('1', "gesz'u"),
('2', "gesz'u"),
('3', "gesz'u"),
('4', "gesz'u"),
('7', "gesz'u"),
('1', 'gesz2'),
('2', 'gesz2'),
('3', 'gesz2'),
('4', 'gesz2'),
('5', 'gesz2'),
('6', 'gesz2'),
('7', 'gesz2'),
('8', 'gesz2'),
('9', 'gesz2'),
'geszimmar',
('2', 'gisz'),
'gudu4',
'ha',
'HA',
'had2',
'hal',
'har',
'HAR',
'he',
'he2',
'hi',
'HI',
'hi@v',
'hu',
'HU',
'hub2',
'hun',
'hur',
'huz',
'ih',
'IH',
('1', 'iku'),
('1/2', 'iku'),
('2', 'iku'),
('3', 'iku'),
('4', 'iku'),
'isztar',
'itu',
'kislah',
'la5',
'lah',
'lah4',
'lah5',
'lah6',
'lal3',
'luh',
'm',
'mah',
'muhaldim',
'n',
'nigar',
'nirah',
'p',
'pesz2',
's',
'sa10',
'sahar',
'ser2',
'siskur2',
'siz',
('3', 'siz'),
'sou',
'sz',
'szagina',
'szah',
'szah2',
'szandana',
('1', 'szar2'),
('2', 'szar2'),
'sze9',
'szii',
'szunigin',
't,ab',
'tah',
'tap',
'tuh',
('1', 'u'),
('2', 'u'),
('3', 'u'),
('4', 'u'),
('5', 'u'),
('6', 'u'),
('7', 'u'),
('8', 'u'),
('9', 'u'),
'udru',
'uh',
'UH',
'uh2',
'UH2',
'UH3',
'uh3',
'ukken',
'umi',
'unu',
'ura',
'x',
'|',
'|A.GAB.LISZ|',
'|KA.TA|',
'|UD.KIB.NU|',
'|UD.KIB|']
We look up the unmapped tokens in the unicode table.
cuneiBlocks = {
"Cuneiform": ("12000", "123FF"),
"Cuneiform Numbers and Punctuation": ("12400", "1247F"),
"Early Dynastic Cuneiform": ("12480", "1254F"),
}
cunicode = {}
for (block, (start, end)) in cuneiBlocks.items():
for u in range(int(start, 16), int(end, 16) + 1):
c = chr(u)
name = uname(c, None)
if name is None:
continue
cunicode[name] = c
mapAddition = {}
notFixed = set()
def getLookup(r):
return r.replace("'", "").upper().replace("SZ", "SH").replace(".", " TIMES ")
for t in sorted(unmapped, key=unkey):
if type(t) is tuple:
if type(t[0]) is int:
(repeat, r) = t
tRepeat = REPEAT.get(repeat, None)
if tRepeat is None:
notFixed.add(t)
continue
tLookup = getLookup(r)
name = f"CUNEIFORM NUMERIC SIGN {tRepeat.upper()} {tLookup}"
c = cunicode.get(name, None)
if c is not None:
mapAddition[t] = c
continue
name = f"CUNEIFORM SIGN {tLookup}"
else:
(fraction, r) = t
tFraction = FRACTION.get(fraction, None)
if tFraction is None:
notFixed.add(t)
continue
tLookup = getLookup(r)
name = f"CUNEIFORM NUMERIC SIGN {tFraction.upper()} {tLookup}"
else:
tLookup = getLookup(t)
name = f"CUNEIFORM SIGN {tLookup}"
c = cunicode.get(name, None)
if c is None:
notFixed.add(t)
else:
mapAddition[t] = c
print(f"fixed {len(mapAddition)} out of {len(unmapped)}")
if mapAddition:
print("FIXED")
for (t, c) in sorted(mapAddition.items(), key=unkey):
print(f"\t{str(t):<15} => {c}")
else:
print("NOTHING FIXED")
if notFixed:
print("UNFIXED")
for t in sorted(notFixed, key=unkey):
print(f"\t{str(t):<15} => ?")
else:
print("ALL FIXED")
fixed 18 out of 182
FIXED
a' => 𒀀
asal2 => 𒀷
duh => 𒂃
HA => 𒄩
ha => 𒄩
hal => 𒄬
HI => 𒄭
hi => 𒄭
HU => 𒄷
hu => 𒄷
hub2 => 𒄸
'i => 𒄿
luh => 𒈛
mah => 𒈤
pesz2 => 𒉾
('1/3', 'disz') => 𒑚
('2/3', 'disz') => 𒑛
('5/6', 'disz') => 𒑜
UNFIXED
&i2 => ?
... => ?
2(disz@t) => ?
ah => ?
AH => ?
alamusz => ?
('1', 'asz') => ?
('1/2', 'asz') => ?
('1/3', 'asz') => ?
('2', 'asz') => ?
('3', 'asz') => ?
('4', 'asz') => ?
('5', 'asz') => ?
('6', 'asz') => ?
('7', 'asz') => ?
('8', 'asz') => ?
('9', 'asz') => ?
babila => ?
babila2 => ?
('1', 'ban2') => ?
('2', 'ban2') => ?
('3', 'ban2') => ?
('4', 'ban2') => ?
('5', 'ban2') => ?
barig => ?
('1', 'barig') => ?
('2', 'barig') => ?
('3', 'barig') => ?
('4', 'barig') => ?
('5', 'barig') => ?
bur'u => ?
('1', "bur'u") => ?
('2', "bur'u") => ?
('3', "bur'u") => ?
('4', "bur'u") => ?
('5', "bur'u") => ?
('1', 'bur3') => ?
('2', 'bur3') => ?
('3', 'bur3') => ?
('4', 'bur3') => ?
('5', 'bur3') => ?
('6', 'bur3') => ?
('8', 'bur3') => ?
('9', 'bur3') => ?
dah => ?
('1', 'disz') => ?
('1/2', 'disz') => ?
('1/4', 'disz') => ?
('1/6', 'disz') => ?
('2', 'disz') => ?
('2/2', 'disz') => ?
('3', 'disz') => ?
('3/4', 'disz') => ?
('4', 'disz') => ?
('5', 'disz') => ?
('6', 'disz') => ?
('7', 'disz') => ?
('8', 'disz') => ?
('9', 'disz') => ?
eh => ?
EH => ?
eri11 => ?
('1', 'esze3') => ?
('2', 'esze3') => ?
('3', 'esze3') => ?
('1', 'gesz') => ?
('9', 'gesz') => ?
gesz'u => ?
('1', "gesz'u") => ?
('2', "gesz'u") => ?
('3', "gesz'u") => ?
('4', "gesz'u") => ?
('7', "gesz'u") => ?
('1', 'gesz2') => ?
('2', 'gesz2') => ?
('3', 'gesz2') => ?
('4', 'gesz2') => ?
('5', 'gesz2') => ?
('6', 'gesz2') => ?
('7', 'gesz2') => ?
('8', 'gesz2') => ?
('9', 'gesz2') => ?
geszimmar => ?
('2', 'gisz') => ?
gudu4 => ?
had2 => ?
har => ?
HAR => ?
he => ?
he2 => ?
hi@v => ?
hun => ?
hur => ?
huz => ?
ih => ?
IH => ?
('1', 'iku') => ?
('1/2', 'iku') => ?
('2', 'iku') => ?
('3', 'iku') => ?
('4', 'iku') => ?
isztar => ?
itu => ?
kislah => ?
la5 => ?
lah => ?
lah4 => ?
lah5 => ?
lah6 => ?
lal3 => ?
m => ?
muhaldim => ?
n => ?
nigar => ?
nirah => ?
p => ?
s => ?
sa10 => ?
sahar => ?
ser2 => ?
siskur2 => ?
siz => ?
('3', 'siz') => ?
sou => ?
sz => ?
szagina => ?
szah => ?
szah2 => ?
szandana => ?
('1', 'szar2') => ?
('2', 'szar2') => ?
sze9 => ?
szii => ?
szunigin => ?
t,ab => ?
tah => ?
tap => ?
tuh => ?
('1', 'u') => ?
('2', 'u') => ?
('3', 'u') => ?
('4', 'u') => ?
('5', 'u') => ?
('6', 'u') => ?
('7', 'u') => ?
('8', 'u') => ?
('9', 'u') => ?
udru => ?
uh => ?
UH => ?
uh2 => ?
UH2 => ?
UH3 => ?
uh3 => ?
ukken => ?
umi => ?
unu => ?
ura => ?
x => ?
| => ?
|A.GAB.LISZ| => ?
|KA.TA| => ?
|UD.KIB.NU| => ?
|UD.KIB| => ?
Most of the remaining problems above got solved by a table provided by Martijn Kokken
MAPPING_SOLUTIONS = dict(
ah=("HIxNUN", "U12134"),
AH=("HIxNUN", "U12134"),
alamusz=("TAxHI", "U122ED"),
babila2=("KA2.AN.RA", "U1218D U1202D U1228F"),
dah=("MU/MU", "U1222D"),
eh=("HIxNUN", "U12134"),
EH=("HIxNUN", "U12134"),
eri11=("AB gunû", "U12015"),
geszimmar=("ŠA6", "U122B7"),
gudu4=("HIxNUN.ME", "U12134 U12228"),
had2=("UD", "U12313"),
har=("HIxAŠ2", "U1212F"),
HAR=("HIxAŠ2", "U1212F"),
he=("HI", "U1212D"),
he2=("GAN", "U120F6"),
hun=("EŠ2", "U120A0"),
hur=("HIxAŠ2", "U1212F"),
huz=("LUM", "U1221D"),
ih=("HIxNUN", "U12134"),
IH=("HIxNUN", "U12134"),
itu=("UDxU.U.U", "U12317"),
KA=("KA TA", "U12157 U122EB"),
kislah=("KI.UD", "U121A0 U12313"),
lah=("UD", "U12313"),
lah4=("DU / DU", "U1207B"),
lah5=("DU.DU", "U1207A U1207A"),
lah6=("DU", "U1207A"),
lal3=("TAxHI", "U122ED"),
muhaldim=("MU", "U1222C"),
nigar=("U.UD.KID", "U1230B U12313 U121A4"),
nirah=("MUŠ", "U12232"),
sa10=("NINDA2xŠE", "U1225A"),
sahar=("IŠ", "U12156"),
siskur2=("AMARxŠE.AMARxŠE", "U1202C U1202C"),
szagina=("GIR3.ARAD", "U1210A U12034"),
szah=("ŠUBUR", "U122DA"),
szah2=("DUN", "U12084"),
szandana=("GAL.NI", "U120F2 U1224C"),
tah=("MU/MU", "U1222D"),
tap=("TAB", "U122F0"),
udru=("AŠ2", "U1203E"),
UH=("HIxNUN", "U12134"),
uh=("HIxNUN", "U12134"),
UH2=("UD.KUŠU2", "U12313 U121B5"),
uh2=("UD.KUŠU2", "U12313 U121B5"),
uh3=("KUŠU2", "U121B5"),
UH3=("KUŠU2", "U121B5"),
ukken=("URUxBAR", "U1233A"),
unu=("AB gunû", "U12015"),
)
MAPPING_SOLUTIONS.update(
{
"1(asz)": ("", "U12038"),
"2(asz)": ("", "U12400"),
"3(asz)": ("", "U12401"),
"4(asz)": ("", "U12402"),
"5(asz)": ("", "U12403"),
"6(asz)": ("", "U12404"),
"7(asz)": ("", "U12405"),
"8(asz)": ("", "U12406"),
"9(asz)": ("", "U12407"),
"1/2(asz)": ("", "U12226"),
"1/3(asz)": ("", "U1245A"),
"1/4(asz)": ("", "U12460"),
"1/8(asz)": ("", "U1245F"),
"babila": ("", "U1218D U1202D"),
"1(ban2)": ("", "U1244F"),
"2(ban2)": ("", "U12450"),
"3(ban2)": ("", "U12451"),
"4(ban2)": ("", "U12452"),
"5(ban2)": ("", "U12454"),
"barig": ("", "U12079"),
"1(barig)": ("", "U12079"),
"2(barig)": ("", "U12079 U12079"),
"3(barig)": ("", "U12079 U12079 U12079"),
"4(barig)": ("", "U1235D"),
"5(barig)": ("", "U12125"),
"bur3": ("", "U1230B"),
"bur'u": ("", "U12434"),
"1(bur3)": ("", "U1230B"),
"2(bur3)": ("", "U1230B U1230B"),
"3(bur3)": ("", "U1230B U1230B U1230B"),
"4(bur3)": ("", "U1240F"),
"5(bur3)": ("", "U12410"),
"6(bur3)": ("", "U12411"),
"7(bur3)": ("", "U12412"),
"8(bur3)": ("", "U12413"),
"9(bur3)": ("", "U12414"),
"1(disz)": ("", "U12079"),
"2(disz)": ("", "U1222B"),
"3(disz)": ("", "U12408"),
"4(disz)": ("", "U12409"),
"5(disz)": ("", "U1240A"),
"6(disz)": ("", "U1240B"),
"7(disz)": ("", "U1240C"),
"8(disz)": ("", "U1240D"),
"9(disz)": ("", "U1240E"),
"1/2(disz)": ("", "U12226"),
"1/3(disz)": ("", "U1245A"),
"1/4(disz)": ("", "U12462"),
"1/6(disz)": ("", "U12461"),
"2/3(disz)": ("", "U1245B"),
"5/6(disz)": ("", "U1245C"),
"13(disz)": ("", "U12399 U12408"),
"disz@t": ("", "U120F5"),
"hi@v": ("", "U1212D"),
"1(iku)": ("", "U12038"),
"2(iku)": ("", "U12400"),
"3(iku)": ("", "U12401"),
"4(iku)": ("", "U12402"),
"5(iku)": ("", "U12403"),
"6(iku)": ("", "U12404"),
"7(iku)": ("", "U12405"),
"8(iku)": ("", "U12406"),
"9(iku)": ("", "U12407"),
"1(esze3)": ("", "U12458"),
"2(esze3)": ("", "U12459"),
"3(esze3)": ("", "U12038 U1230B"),
"gesz2": ("", "U12415"),
"1(gesz2)": ("", "U12415"),
"gesz'u": ("", "U1241E"),
"la5": ("", "U121F3"),
"szar2": ("", "U122B9"),
"1(u)": ("", "U1230B"),
"2(u)": ("", "U12399"),
"3(u)": ("", "U1230D"),
"4(u)": ("", "U1240F"),
"5(u)": ("", "U12410"),
"6(u)": ("", "U12411"),
"7(u)": ("", "U12412"),
"8(u)": ("", "U12413"),
"9(u)": ("", "U12414"),
}
)
MAPPING_SOLUTIONSX = {}
for (token, (grapheme, uniChars)) in MAPPING_SOLUTIONS.items():
uniStr = "".join(chr(int(uc[1:], 16)) for uc in uniChars.split())
MAPPING_SOLUTIONSX[token] = uniStr
MAPPING_SOLUTIONSX
{'ah': '𒄴',
'AH': '𒄴',
'alamusz': '𒋭',
'babila2': '𒆍𒀭𒊏',
'dah': '𒈭',
'eh': '𒄴',
'EH': '𒄴',
'eri11': '𒀕',
'geszimmar': '𒊷',
'gudu4': '𒄴𒈨',
'had2': '𒌓',
'har': '𒄯',
'HAR': '𒄯',
'he': '𒄭',
'he2': '𒃶',
'hun': '𒂠',
'hur': '𒄯',
'huz': '𒈝',
'ih': '𒄴',
'IH': '𒄴',
'itu': '𒌗',
'KA': '𒅗𒋫',
'kislah': '𒆠𒌓',
'lah': '𒌓',
'lah4': '𒁻',
'lah5': '𒁺𒁺',
'lah6': '𒁺',
'lal3': '𒋭',
'muhaldim': '𒈬',
'nigar': '𒌋𒌓𒆤',
'nirah': '𒈲',
'sa10': '𒉚',
'sahar': '𒅖',
'siskur2': '𒀬𒀬',
'szagina': '𒄊𒀴',
'szah': '𒋚',
'szah2': '𒂄',
'szandana': '𒃲𒉌',
'tah': '𒈭',
'tap': '𒋰',
'udru': '𒀾',
'UH': '𒄴',
'uh': '𒄴',
'UH2': '𒌓𒆵',
'uh2': '𒌓𒆵',
'uh3': '𒆵',
'UH3': '𒆵',
'ukken': '𒌺',
'unu': '𒀕',
'1(asz)': '𒀸',
'2(asz)': '𒐀',
'3(asz)': '𒐁',
'4(asz)': '𒐂',
'5(asz)': '𒐃',
'6(asz)': '𒐄',
'7(asz)': '𒐅',
'8(asz)': '𒐆',
'9(asz)': '𒐇',
'1/2(asz)': '𒈦',
'1/3(asz)': '𒑚',
'1/4(asz)': '𒑠',
'1/8(asz)': '𒑟',
'babila': '𒆍𒀭',
'1(ban2)': '𒑏',
'2(ban2)': '𒑐',
'3(ban2)': '𒑑',
'4(ban2)': '𒑒',
'5(ban2)': '𒑔',
'barig': '𒁹',
'1(barig)': '𒁹',
'2(barig)': '𒁹𒁹',
'3(barig)': '𒁹𒁹𒁹',
'4(barig)': '𒍝',
'5(barig)': '𒄥',
'bur3': '𒌋',
"bur'u": '𒐴',
'1(bur3)': '𒌋',
'2(bur3)': '𒌋𒌋',
'3(bur3)': '𒌋𒌋𒌋',
'4(bur3)': '𒐏',
'5(bur3)': '𒐐',
'6(bur3)': '𒐑',
'7(bur3)': '𒐒',
'8(bur3)': '𒐓',
'9(bur3)': '𒐔',
'1(disz)': '𒁹',
'2(disz)': '𒈫',
'3(disz)': '𒐈',
'4(disz)': '𒐉',
'5(disz)': '𒐊',
'6(disz)': '𒐋',
'7(disz)': '𒐌',
'8(disz)': '𒐍',
'9(disz)': '𒐎',
'1/2(disz)': '𒈦',
'1/3(disz)': '𒑚',
'1/4(disz)': '𒑢',
'1/6(disz)': '𒑡',
'2/3(disz)': '𒑛',
'5/6(disz)': '𒑜',
'13(disz)': '𒎙𒐈',
'disz@t': '𒃵',
'hi@v': '𒄭',
'1(iku)': '𒀸',
'2(iku)': '𒐀',
'3(iku)': '𒐁',
'4(iku)': '𒐂',
'5(iku)': '𒐃',
'6(iku)': '𒐄',
'7(iku)': '𒐅',
'8(iku)': '𒐆',
'9(iku)': '𒐇',
'1(esze3)': '𒑘',
'2(esze3)': '𒑙',
'3(esze3)': '𒀸𒌋',
'gesz2': '𒐕',
'1(gesz2)': '𒐕',
"gesz'u": '𒐞',
'la5': '𒇳',
'szar2': '𒊹',
'1(u)': '𒌋',
'2(u)': '𒎙',
'3(u)': '𒌍',
'4(u)': '𒐏',
'5(u)': '𒐐',
'6(u)': '𒐑',
'7(u)': '𒐒',
'8(u)': '𒐓',
'9(u)': '𒐔'}
print(f"{len(multiple):>3} ambiguously mapped readings")
for r in sorted(multiple):
unis = multiple[r]
uniStr = " - ".join(sorted(unis))
print(f"{r} => ({len(unis)}) => {uniStr}")
58 ambiguously mapped readings 2 => (3) => 𒈫 - 𒈫𒌍 - 𒐀 IA => (2) => 𒅀 - 𒉿 IL => (2) => 𒀧 - 𒅋 IRI => (2) => 𒅕 - 𒌷 KAM => (2) => 𒄭𒁁 - 𒄰 LUM => (2) => 𒈝 - 𒋞 USZ => (2) => 𒍑 - 𒍖 UZ => (2) => 𒊻 - 𒍖 WA => (2) => 𒁀 - 𒉿 ba4 => (3) => 𒀀𒀭𒂷 - 𒂷 - 𒍝𒂷𒂷 ba6 => (2) => 𒁀𒌑 - 𒌑 bara2 => (2) => 𒁁 - 𒁈 bum => (2) => 𒅤 - 𒆃 buru14 => (2) => 𒂘 - 𒂙 da2 => (2) => 𒋫 - 𒋬 dabin => (2) => 𒂠𒊺 - 𒍥𒊺 dilmun => (3) => 𒉌𒌇 - 𒊩𒄸 - 𒊩𒌇 eri => (2) => 𒅕 - 𒌷 erisz => (2) => 𒊩𒈠 - 𒊩𒌆 gala => (3) => 𒃲 - 𒍑𒆪 - 𒍓 gin7 => (2) => 𒁶 - 𒄀 gurusz => (2) => 𒄨 - 𒆗 ia => (2) => 𒅀 - 𒉿 idim => (2) => 𒁁 - 𒅂 ii => (2) => 𒅀 - 𒉿 il => (2) => 𒀧 - 𒅋 iri => (2) => 𒅕 - 𒌷 isz8 => (2) => 𒀹 - 𒌋 iu => (2) => 𒅀 - 𒉿 kam => (2) => 𒄭𒁁 - 𒄰 kesz2 => (2) => 𒂡 - 𒆟 kesz3 => (2) => 𒋙𒀭𒄲 - 𒋙𒀭𒄲𒆠 limmu2 => (2) => 𒇹 - 𒐂 lum => (2) => 𒈝 - 𒋞 munu4 => (2) => 𒉽𒉽 - 𒉽𒊺𒉽 ne3 => (2) => 𒄊 - 𒊊 nergal => (2) => 𒄊𒀕𒃲 - 𒊊𒀕𒃲 pa2 => (2) => 𒁀 - 𒁀𒌑 pirig => (2) => 𒄊 - 𒊊 puzur4 => (2) => 𒅤𒊭 - 𒆃𒊭 s,ur2 => (2) => 𒈲 - 𒊨 sig17 => (2) => 𒄀 - 𒆬 sze20 => (2) => 𒂠 - 𒅆 t,a2 => (2) => 𒋫 - 𒋬 te3 => (2) => 𒉀 - 𒉁 til => (2) => 𒁁 - 𒌀 tim2 => (2) => 𒋻 - 𒌈 ug2 => (2) => 𒄊 - 𒊊 uri5 => (2) => 𒋀𒀊 - 𒌵 us => (2) => 𒊻 - 𒍖 usa => (2) => 𒐍 - 𒑄 usz => (2) => 𒍑 - 𒍖 usz2 => (2) => 𒁁 - 𒍗 uz => (2) => 𒊻 - 𒍖 wa => (2) => 𒁀 - 𒉿 wa2 => (2) => 𒁀 - 𒉌 zi3 => (2) => 𒂠 - 𒍥 ziz2 => (2) => 𒀾 - 𒍩
Make an excel sheet of all ambiguously mapped readings. For each such reading, collect 4 examples on 4 distinct lines (if possible).
The sheet has columns for:
def unameStr(glyphstr):
return " + ".join(
uname(g).replace("CUNEIFORM", "").replace("SIGN", "").strip() for g in glyphstr
)
print(f"{len(unique):>3} uniquely mapped readings")
for r in sorted(unique):
print(f"{r:>10} => {unique[r]}")
905 uniquely mapped readings
A => 𒀀
A2 => 𒀉
AB => 𒀊
AD => 𒀜
AG => 𒀝
AK => 𒀝
AL => 𒀠
AM => 𒄠
AN => 𒀭
AR => 𒅈
ARAD => 𒀴
ARAD2 => 𒀵
AS, => 𒊍
AS2 => 𒀾
ASZ => 𒀸
AZ => 𒊍
BA => 𒁀
BAD => 𒁁
BAR => 𒁇
BE => 𒁁
BI => 𒁉
BU => 𒁍
BUR => 𒁓
DA => 𒁕
DAM => 𒁮
DI => 𒁲
DIM => 𒁴
DIN => 𒁷
DISZ => 𒁹
DU => 𒁺
DU10 => 𒄭
DUL3 => 𒊨
E => 𒂊
EDIN => 𒂔
EK => 𒅅
EL => 𒂖
ER => 𒅕
GA => 𒂵
GAG => 𒆕
GAL => 𒃲
GAN2 => 𒃷
GAR => 𒃻
GAZ => 𒄤
GESZ => 𒄑
GI => 𒄀
GIR => 𒄫
GIR2 => 𒄈
GU => 𒄖
I => 𒄿
IB => 𒅁
ID => 𒀉
IG => 𒅅
IK => 𒅅
IL2 => 𒅍
IM => 𒅎
IN => 𒅔
IR => 𒅕
ISZ => 𒅖
IZ => 𒄑
KA => 𒅗
KAB => 𒆏
KI => 𒆠
KIB => 𒄒
KU => 𒆪
KUM => 𒄣
KUR => 𒆳
Ku => 𒆪
LA => 𒆷
LAM => 𒇴
LE => 𒇷
LI => 𒇷
LU => 𒇻
LU2 => 𒇽
MA => 𒈠
ME => 𒈨
MI => 𒈪
NA => 𒈾
NAM => 𒉆
NE => 𒉈
NI => 𒉌
NIG2 => 𒃻
NIM => 𒉏
NIN => 𒊩𒌆
NU => 𒉡
NUN => 𒉣
PA => 𒉺
PI => 𒉿
PU3 => 𒅤
RA => 𒊏
RI => 𒊑
RU => 𒊒
Ra => 𒊏
S,I => 𒍢
SA => 𒊓
SAG => 𒊕
SAR => 𒊬
SIG => 𒋝
SIG7 => 𒅊
SIPA => 𒉺𒇻
SU => 𒋢
SUM => 𒋧
SZA => 𒊭
SZE => 𒊺
SZE3 => 𒂠
SZESZ => 𒋀
SZI => 𒅆
SZIM => 𒋆
SZIR => 𒋓
SZU => 𒋗
TA => 𒋫
TAB => 𒑊
TAM => 𒌓
TAR => 𒋻
TE => 𒋼
TI => 𒋾
TIM => 𒁴
TU => 𒌅
TUG2 => 𒌆
TUL2 => 𒇥
TUM => 𒌈
TUR => 𒌉
U2 => 𒌑
U3 => 𒅇
U4 => 𒌓
UB => 𒌒
UD => 𒌓
UG => 𒊌
UGU => 𒌋𒅗
UK => 𒊌
UL => 𒌌
UM => 𒌝
UR => 𒌨
UTU => 𒌓
WE => 𒉿
WI => 𒉿
ZA => 𒍝
ZE => 𒍣
ZI => 𒍣
ZI2 => 𒍢
ZU => 𒍪
ZUM => 𒍮
a => 𒀀
a2 => 𒀉
a3 => 𒉿
ab => 𒀊
ab2 => 𒀖
abul => 𒆍𒃲
abzu => 𒍪𒀊
ad => 𒀜
adab => 𒌓𒉣
ag => 𒀝
ag2 => 𒉘
aga => 𒂆
agrig => 𒅆𒁾
ak => 𒀝
akszak => 𒌔
al => 𒀠
alam => 𒀩
alan => 𒀩
alim => 𒄍
am => 𒄠
am3 => 𒀀𒀭
ama => 𒂼
amar => 𒀫
an => 𒀭
ansze => 𒄏
ap => 𒀊
ap2 => 𒀖
apin => 𒀳
aq => 𒀝
ar => 𒅈
ar3 => 𒄯
as => 𒊍
as, => 𒊍
as,2 => 𒀾
as2 => 𒀾
asal => 𒍂
asar => 𒍂
asz => 𒀸
asz2 => 𒀾
asza5 => 𒃷
aszgab => 𒀿
asznan => 𒊺𒌁
at => 𒀜
at, => 𒀜
az => 𒊍
az2 => 𒀾
az3 => 𒀸
azlag2 => 𒌆
ba => 𒁀
ba2 => 𒉺
babbar => 𒌓
bad3 => 𒂦
bal => 𒁄
bala => 𒁄
ban => 𒉼
ban2 => 𒑏
ban3 => 𒌉
banda3 => 𒌉
banesz => 𒑑
banszur => 𒍎
bappir => 𒋋
bar => 𒁇
bat => 𒁁
be => 𒁁
be2 => 𒁉
be4 => 𒁀
bi => 𒁉
bi2 => 𒉈
bi3 => 𒉿
bi4 => 𒁁
bil => 𒉈
bil2 => 𒉋
bir2 => 𒌓
bir4 => 𒂔
bisz => 𒄫
bu => 𒁍
bun2 => 𒅮
bur => 𒁓
bur3 => 𒌋
buranun => 𒌓𒄒𒉣
d => 𒀭
da => 𒁕
da3 => 𒆕
dab => 𒁳
dab5 => 𒆪
dag => 𒁖
dagal => 𒂼
dal => 𒊑
dam => 𒁮
dam2 => 𒌓
dan => 𒄨
daq => 𒁖
dar => 𒁯
dar2 => 𒅁
dasz => 𒌨
de => 𒁲
de2 => 𒌣
de3 => 𒉈
de4 => 𒋼
de8 => 𒊹
de9 => 𒋾
di => 𒁲
di12 => 𒋼
di2 => 𒊹
di3 => 𒋾
di8 => 𒌣
dib => 𒁳
dida => 𒁉𒌑𒊓
didli => 𒐀
dil => 𒀸
dim => 𒁴
dim2 => 𒁶
dim4 => 𒉽𒉽
din => 𒁷
dingir => 𒀭
diri => 𒋛𒀀
dirig => 𒋛𒀀
disz => 𒁹
du => 𒁺
du10 => 𒄭
du11 => 𒅗
du2 => 𒌅
du3 => 𒆕
du5 => 𒂅
du6 => 𒇯
du7 => 𒌌
du8 => 𒂃
dub => 𒁾
dug => 𒂁
dug3 => 𒄭
dul3 => 𒊨
dul5 => 𒌆
dum => 𒌈
dumu => 𒌉
dur => 𒄙
dur4 => 𒄒
duru5 => 𒀀
dusu => 𒅍
dusu2 => 𒀲𒅇
e => 𒂊
e2 => 𒂍
e3 => 𒌓𒁺
ea => 𒀀
eb => 𒅁
ed => 𒀉
edin => 𒂔
eg => 𒅅
egir => 𒂕
ek => 𒅅
el => 𒂖
el2 => 𒅋
el3 => 𒀭
elam => 𒉏
em => 𒅎
eme => 𒅴
eme6 => 𒀲𒊩
en => 𒂗
en6 => 𒅔
engar => 𒀳
enku => 𒍠𒄩
ensi2 => 𒑐𒋼𒋛
ep => 𒅁
eq => 𒅅
er => 𒅕
er2 => 𒀀𒅆
er3 => 𒀴
eren2 => 𒂟
eresz2 => 𒉀
erim => 𒂟
erin => 𒂞
erin2 => 𒂟
es => 𒄑
es, => 𒄑
esir => 𒀀𒇒
esz => 𒌍
esz15 => 𒅖
esz18 => 𒀹
esz2 => 𒂠
esz3 => 𒀊
esz4 => 𒁹
esza => 𒀀𒌁
esze3 => 𒑘
et => 𒀉
et, => 𒀉
ez => 𒄑
ezem => 𒂡
ga => 𒂵
ga2 => 𒂷
gab => 𒃮
gaba => 𒃮
gada => 𒃰
gag => 𒆕
gakkul => 𒌋𒁵
gal => 𒃲
gal2 => 𒅅
gam => 𒑲
gam2 => 𒄰
gan => 𒃶
gan2 => 𒃷
ganba => 𒆠𒇴
gar => 𒃻
gar3 => 𒃼
gaz => 𒄤
ge => 𒄀
ge5 => 𒆠
ge6 => 𒈪
geme => 𒊩
geme2 => 𒊩𒆳
gesz => 𒄑
gesz2 => 𒁹
gesztin => 𒃾
gesztu2 => 𒄑𒌆𒉿
gi => 𒄀
gi2 => 𒆤
gi4 => 𒄄
gi5 => 𒆠
gi6 => 𒈪
gi7 => 𒂠
gibil => 𒉋
gid2 => 𒁍
gidri => 𒉺
gig => 𒈪𒉭
gigir => 𒇀
gim => 𒁶
gin => 𒁺
gin2 => 𒂅
gin3 => 𒆳
gir => 𒄫
gir14 => 𒄩
gir2 => 𒄈
gir3 => 𒄊
gir8 => 𒆸
giri17 => 𒅗
giri3 => 𒄊
gissu => 𒄑𒈪
gisz => 𒄑
gu => 𒄖
gu2 => 𒄘
gu4 => 𒄞
gu5 => 𒆪
gu7 => 𒅥
gub => 𒁺
gud => 𒄞
gug => 𒍝𒄢
gul => 𒄢
gum2 => 𒈝
gur => 𒄥
gur10 => 𒆥
gur11 => 𒂵
gur16 => 𒆳
gur8 => 𒋽
guru7 => 𒄦
i => 𒄿
i2 => 𒐊
i3 => 𒉌
i7 => 𒀀𒇉
ia2 => 𒐊
ia3 => 𒉌
ib => 𒅁
ib2 => 𒌈
ibila => 𒌉𒍑
id => 𒀉
id2 => 𒀀𒇉
idigna => 𒈦𒄘𒃼
ig => 𒅅
igi => 𒅆
ik => 𒅅
iku => 𒃷
il2 => 𒅍
il3 => 𒀭
il5 => 𒂖
ili5 => 𒂖
illat => 𒆜𒆳
im => 𒅎
imin => 𒑂
imma3 => 𒅊
in => 𒅔
in4 => 𒂗
ina => 𒀸
inanna => 𒈹
inim => 𒅗
ip => 𒅁
iq => 𒅅
ir => 𒅕
ir3 => 𒀴
is => 𒄑
is, => 𒄑
is2 => 𒅖
is3 => 𒀊
is4 => 𒀾
isz => 𒅖
isz2 => 𒆜
isz3 => 𒌍
isz7 => 𒀊
iszkur => 𒅎
isztaran => 𒅗𒁲
it => 𒀉
it, => 𒀉
iti => 𒌚
iz => 𒄑
ka => 𒅗
ka2 => 𒆍
ka3 => 𒂵
ka9 => 𒋃
kab => 𒆏
kak => 𒆕
kal => 𒄨
kal2 => 𒃲
kalag => 𒄨
kalam => 𒌦
kan => 𒃶
kan2 => 𒃷
kap => 𒆏
kar => 𒋼𒀀
kar2 => 𒃸
kar3 => 𒃼
kas4 => 𒁽
kaskal => 𒆜
kasz => 𒁉
ke => 𒆠
ke2 => 𒄀
ke4 => 𒆤
ki => 𒆠
ki2 => 𒄀
ki3 => 𒀝
ki5 => 𒁶
kid => 𒆤
kikken2 => 𒄯𒄯
kilib => 𒆸
kin => 𒆥
kir => 𒄫
kiri6 => 𒊬
kis2 => 𒄑
kisz => 𒆧
kiszib => 𒈩
kiszib3 => 𒁾
ku => 𒆪
ku13 => 𒄣
ku2 => 𒅥
ku3 => 𒆬
ku4 => 𒆮
ku5 => 𒋻
ku6 => 𒄩
kul => 𒆰
kul2 => 𒄢
kum => 𒄣
kun => 𒆲
kup4 => 𒆤
kur => 𒆳
kur2 => 𒉽
kurun2 => 𒁷
kuruszda => 𒆯
kusz => 𒋢
kusz3 => 𒌑
la => 𒆷
la2 => 𒇲
lagasz => 𒋓𒁓𒆷
lal2 => 𒇳
lam => 𒇴
lam2 => 𒉈
lam5 => 𒅆
lamma => 𒄨
larsa => 𒌓𒀕
le => 𒇷
le2 => 𒉌
lem => 𒅆
li => 𒇷
li2 => 𒉌
li3 => 𒅆
libir => 𒅆𒂠
lik => 𒌨
lil2 => 𒆤
lim => 𒅆
lim3 => 𒇴
liq => 𒌨
lu => 𒇻
lu2 => 𒇽
lu4 => 𒈝
lugal => 𒈗
lukur => 𒊩𒈨
lum2 => 𒅆
ma => 𒈠
ma2 => 𒈣
mal => 𒂷
man => 𒌋𒌋
mar => 𒈥
mar2 => 𒀫
marduk => 𒀫𒌓
mas => 𒈦
masz => 𒈦
masz2 => 𒈧
maszkim => 𒑐𒁽
maszkim3 => 𒑐𒁺
me => 𒈨
me2 => 𒈪
mesz => 𒈨𒌍
mi => 𒈪
mi2 => 𒊩
mi3 => 𒈨
mil => 𒅖
mu => 𒈬
mug => 𒈮
mun => 𒁵
munus => 𒊩
mur => 𒄯
musz => 𒈲
musz5 => 𒋀
muszen => 𒄷
na => 𒈾
na2 => 𒈿
na4 => 𒉌𒌓
nag2 => 𒉀
nagar => 𒉄
nagga => 𒀭𒈾
nam => 𒉆
nam3 => 𒉏
nanna => 𒌶𒆠
nansze => 𒀏
nar => 𒈜
ne => 𒉈
ne2 => 𒉌
ni => 𒉌
ni3 => 𒃻
ni7 => 𒉏
nibru => 𒂗𒆤
nidaba => 𒊺𒉀
nidba2 => 𒉻𒈹
nig2 => 𒃻
nigin3 => 𒌋𒌓𒆤
nigin6 => 𒀒
nim => 𒉏
nimgir => 𒂆
nin => 𒊩𒌆
nina => 𒀏
ninda => 𒃻
nir => 𒉪
nis => 𒌋𒌋
nita => 𒍑
nita2 => 𒀴
nu => 𒉡
nu2 => 𒈿
num => 𒉏
num2 => 𒈝
numun => 𒆰
nun => 𒉣
nunuz => 𒉭
pa => 𒉺
pa12 => 𒉿
pa3 => 𒅆𒊒
pa4 => 𒉽
pa5 => 𒉽𒂊
pal => 𒁄
par => 𒌓
par2 => 𒁇
pe => 𒉿
pe2 => 𒁉
pe3 => 𒁁
pesz => 𒄫
pi => 𒉿
pi2 => 𒁉
pi3 => 𒁁
pi4 => 𒅗
pil => 𒉈
pil2 => 𒉋
pir => 𒌓
pisan => 𒂷
pisz => 𒄫
pu => 𒁍
pur => 𒁓
puzur => 𒌋
puzur2 => 𒌋𒌋
qa => 𒋡
qa2 => 𒂵
qa3 => 𒅗
qal => 𒃲
qal4 => 𒄨
qam2 => 𒄰
qar => 𒃼
qar3 => 𒃻
qe => 𒆥
qe2 => 𒆠
qe3 => 𒄀
qer => 𒄫
qi => 𒆥
qi2 => 𒆠
qi3 => 𒄀
qi4 => 𒄄
qir => 𒄫
qu => 𒄣
qu2 => 𒆪
qu3 => 𒄖
qul => 𒆰
qul2 => 𒄢
qum => 𒄣
qur => 𒄥
qur2 => 𒆳
ra => 𒊏
ra2 => 𒁺
ram => 𒉘
rasz => 𒆜
re => 𒊑
ri => 𒊑
ri2 => 𒌷
rik => 𒋆
rim => 𒆸
rim5 => 𒀸
ru => 𒊒
ru3 => 𒀸
rum => 𒀸
ruq => 𒊿
s,a => 𒍝
s,a3 => 𒀭
s,ar => 𒇡
s,e => 𒍢
s,e2 => 𒍣
s,i => 𒍢
s,i2 => 𒍣
s,il2 => 𒈪
s,ir => 𒈲
s,u => 𒍮
s,u2 => 𒍪
s,um => 𒍮
s,ur => 𒀫
sa => 𒊓
sa12 => 𒊕
sa2 => 𒁲
sa3 => 𒍝
sa6 => 𒊷
sag => 𒊕
sag10 => 𒅆𒂟
sag11 => 𒆥
saga => 𒊕
sak => 𒊕
sal => 𒊩
sal2 => 𒁲
sanga => 𒋃
sar => 𒊬
se => 𒋛
se2 => 𒍣
se3 => 𒋧
si => 𒋛
si2 => 𒍣
si3 => 𒋧
si4 => 𒋜
sig => 𒋝
sig2 => 𒋠
sig4 => 𒋞
sig5 => 𒅆𒂟
siki => 𒋠
sikil => 𒂖
sila => 𒋻
sila3 => 𒋡
sila4 => 𒃢
silig => 𒍂
silim => 𒁲
sim => 𒉆
simug => 𒌣
sin => 𒌍
sin2 => 𒉆
sipa => 𒉺𒇻
sipad => 𒉺𒇻
sir2 => 𒁍
sir3 => 𒂡
su => 𒋢
su2 => 𒍪
su3 => 𒋤
su7 => 𒇭
suen => 𒂗𒍪
sukkal => 𒈛
sum => 𒋧
sum2 => 𒍮
sun2 => 𒄢
sur => 𒋩
sza => 𒊭
sza13 => 𒊹
sza2 => 𒃻
sza3 => 𒊮
szabra => 𒑐𒀠
szakkan2 => 𒄊
szal => 𒊩
szal2 => 𒋡
szam => 𒌑
szam3 => 𒉓
szar => 𒊬
szar2 => 𒊹
szara2 => 𒇋
szat => 𒆳
sze => 𒊺
sze2 => 𒋛
sze3 => 𒂠
szen => 𒊿
szennur => 𒄒
szesz => 𒋀
szi => 𒅆
szi2 => 𒋛
szi3 => 𒋝
szid => 𒋃
szim => 𒋆
szinig => 𒋒
szitim => 𒁶
szu => 𒋗
szu2 => 𒋙
szu3 => 𒂠
szub => 𒊒
szubur => 𒋚
szuku => 𒉻
szul => 𒂄
szum => 𒋳
szum2 => 𒋧
szur => 𒋩
szur2 => 𒊨
szur3 => 𒋓
szur4 => 𒇳𒊬
szusz3 => 𒅖
t,a => 𒁕
t,a3 => 𒄭
t,ab6 => 𒄭
t,am => 𒁮
t,am2 => 𒌓
t,ar => 𒋻
t,e => 𒁲
t,e2 => 𒊹
t,e4 => 𒋼
t,e6 => 𒋾
t,i => 𒁲
t,i2 => 𒊹
t,i3 => 𒋾
t,im => 𒁴
t,u => 𒂅
t,u2 => 𒌅
t,u3 => 𒁺
t,ul => 𒇥
t,um => 𒌈
t,up => 𒁾
t,ur => 𒄙
t,ur4 => 𒄒
ta => 𒋫
ta2 => 𒁕
ta3 => 𒋳
tab => 𒑊
tag2 => 𒁖
tak => 𒋳
tak2 => 𒁖
tak4 => 𒋺
taka4 => 𒋺
tal => 𒊑
tam => 𒌓
tam2 => 𒁮
tam3 => 𒁴
tam4 => 𒌈
taq => 𒋳
taq2 => 𒁖
tar => 𒋻
tar2 => 𒁯
tas => 𒌨
taskarin => 𒌆
tasz => 𒌨
te => 𒋼
te2 => 𒊹
te4 => 𒉈
te9 => 𒋾
tel => 𒁁
tem => 𒁴
ter => 𒌁
tesz2 => 𒌨
ti => 𒋾
ti2 => 𒊹
ti3 => 𒁴
ti7 => 𒋼
tibira => 𒍏𒉄
tik => 𒄘
tim => 𒁴
tir => 𒌁
tiszpak => 𒈽
tu => 𒌅
tu2 => 𒌓
tu3 => 𒁺
tug => 𒌇
tug2 => 𒌆
tukul => 𒆪
tul => 𒌋𒌆
tul2 => 𒇥
tum => 𒌈
tum8 => 𒁴
tun3 => 𒂅
tup => 𒁾
tur => 𒌉
tur2 => 𒄙
tur3 => 𒉣𒇬
tur4 => 𒄒
u => 𒌋
u2 => 𒌑
u3 => 𒅇
u4 => 𒌓
u8 => 𒇇
u9 => 𒂦
ub => 𒌒
ubi2 => 𒋦
ud => 𒌓
ud5 => 𒍚
udu => 𒇻
ug => 𒊌
ug3 => 𒌦
ugula => 𒉺
uk => 𒊌
ul => 𒌌
um => 𒌝
umbin => 𒌢
umma => 𒄑𒆵
un => 𒌦
unken => 𒌺
unug => 𒀕
up => 𒌒
uq => 𒊌
ur => 𒌨
ur2 => 𒌫
ur3 => 𒃡
ur4 => 𒌴
ur5 => 𒄯
urasz => 𒅁
uri2 => 𒋀𒀕
urta => 𒅁
uru => 𒌷
uru4 => 𒀳
uruda => 𒍏
urudu => 𒍏
us, => 𒊻
us,2 => 𒍑
us,4 => 𒊍
us2 => 𒍑
usan3 => 𒉮
usz10 => 𒊻
ut => 𒌓
ut, => 𒌓
utu => 𒌓
uz2 => 𒍑
uz4 => 𒊍
uzu => 𒍜
war => 𒁇
we => 𒉿
wi => 𒉿
wil => 𒅖
wu => 𒉿
yi => 𒉿
za => 𒍝
za3 => 𒍠
zabala4 => 𒈹𒍝𒀕
zabar => 𒌓𒅗𒈦
zadim => 𒈯
zal => 𒉌
zalag2 => 𒂟
zar => 𒇡
ze => 𒍣
ze2 => 𒍢
zi => 𒍣
zi2 => 𒍢
zib => 𒍦
zid2 => 𒂠
zimbir => 𒌓𒄒𒉣
zir3 => 𒈲
zu => 𒍪
zu2 => 𒅗
zum => 𒍮
zur => 𒀫
pairs = {}
for (k, vs) in multiple.items():
pairs[k] = sorted(vs)[0]
for (t, v) in mapAddition.items():
k = f"{t[0]}({t[1]})" if type(t) is tuple else t
pairs[k] = v
for (k, v) in MAPPING_SOLUTIONSX.items():
pairs[k] = v
for (k, v) in unique.items():
pairs[k] = v
Solutions already found for OldBabylonian
obbMappingFile = os.path.expanduser(
"~/github/Nino-cunei/oldbabylonian/characters/mapping.tsv"
)
obbMapping = {}
with open(obbMappingFile) as fh:
for line in fh:
(name, uni) = line.rstrip().split("\t")
obbMapping[name] = uni
ok = set()
diff = set()
new = set()
for (name, uni) in obbMapping.items():
if name in pairs:
if uni == pairs[name]:
ok.add(name)
else:
diff.add(name)
else:
new.add(name)
print(f"{len(new)} new")
print(f"{len(diff)} diff")
print(f"{len(ok)} ok")
print("NEW")
for name in sorted(new):
print(f"\t{name:<20} => {obbMapping[name]}")
print("DIFF")
for name in sorted(diff):
print(f"\t{name:<20} => OBB: {obbMapping[name]}, CANONICAL: {pairs[name]}")
20 new 4 diff 940 ok NEW 1(bur'u) => 𒐴 1(gesz'u) => 𒐞 1(szar2) => 𒊹 2(bur'u) => 𒐵 2(gesz'u) => 𒐟 2(gesz2) => 𒐖 2(gisz) => 𒄑 2(szar2) => 𒐣 3(bur'u) => 𒐶 3(gesz'u) => 𒐠 3(gesz2) => 𒐗 4(bur'u) => 𒐸 4(gesz'u) => 𒐡 4(gesz2) => 𒐘 5(bur'u) => 𒐹 5(gesz2) => 𒐙 6(gesz2) => 𒐚 7(gesz2) => 𒐛 8(gesz2) => 𒐜 9(gesz2) => 𒐝 DIFF 2(disz) => OBB: 𒁹, CANONICAL: 𒈫 2(u) => OBB: 𒌋, CANONICAL: 𒎙 3(u) => OBB: 𒌋, CANONICAL: 𒌍 gesz2 => OBB: 𒐕, CANONICAL: 𒁹
We add the new ones to our mapping.
In the cases where the previous OBB mapping was different, the new mapping is the right one.
So:
for (name, uni) in obbMapping.items():
if name in pairs:
continue
pairs[name] = uni
with open(MAPPING_FILE, "w") as mf:
for (k, v) in sorted(pairs.items()):
mf.write(f"{k}\t{v}\n")
print(f"{len(pairs)} entries written to {MAPPING_FILE}")
1123 entries written to /Users/dirk/github/Nino-cunei/signs/characters/mapping.tsv