Spaces:
Sleeping
Sleeping
Commit ยท
2c93df1
1
Parent(s): e45bbbb
Taqtee3
Browse files- allam/shakl.txt +17 -0
- app.py +55 -20
- garood.gold +2 -0
- garood.py +26 -1
- garood.tmp +11 -43
- garood.yaml +4 -4
allam/shakl.txt
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
ูู
ุจุชุดููู ุงูุจูุช ุงูุขุชู ุชุดูููุง ุชุงู
ุง ูุงู
ูุงุ ูุง ุชุถู ุฃู ุชุญุฐู ุฃู ุญุฑููุ ููุท ูู
ุจุฅุถุงูุฉ ุญุฑูุงุช ุงูุชุดููู ูุงูุณููู ูููุง ุจุทุฑููุฉ ุตุญูุญุฉ
|
| 2 |
+
|
| 3 |
+
Input: ูู ุบุงุฏุฑ ุงูุดุนุฑุงุก ู
ู ู
ุชุฑุฏู
* ุฃู
ูู ุนุฑูุช ุงูุฏุงุฑ ุจุนุฏ ุชููู
|
| 4 |
+
|
| 5 |
+
Output: ูููู ุบูุงุฏูุฑู ุงูุดููุนูุฑูุงุกู ู
ููู ู
ูุชูุฑูุฏููู
ู * ุฃูู
ู ูููู ุนูุฑูููุชู ุงูุฏููุงุฑู ุจูุนูุฏู ุชููููููู
ู
|
| 6 |
+
####
|
| 7 |
+
|
| 8 |
+
Input: ูุฅุฐุง ุงูุฌุจุงู ููุงู ููู
ูุฑููุฉ * ุฎููุง ุนููู ู
ู ุงุฒุฏุญุงู
ุงูุฌุญูู
|
| 9 |
+
Output: ูู ุฅูุฐูุง ุงููุฌูุจูุงูู ููููุงูู ููููู
ู ููุฑููููุฉู * ุฎูููููุงู ุนููููููู ู
ููู ุงุฒูุฏูุญูุงู
ู ุงููุฌูุญููููู
|
| 10 |
+
####
|
| 11 |
+
|
| 12 |
+
Input: ุฃุนูุงู ุฑุณู
ุงูุฏุงุฑ ูู
ูุชููู
... ุญุชู ุชููู
ูุงูุฃุตู
ุงูุฃุนุฌู
|
| 13 |
+
Output: ุฃูุนูููุงูู ุฑูุณูู
ู ุงูุฏููุงุฑู ููู
ู ููุชููููููู
ู * ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃูุนูุฌูู
ู
|
| 14 |
+
####
|
| 15 |
+
|
| 16 |
+
Input: $input$
|
| 17 |
+
Output:
|
app.py
CHANGED
|
@@ -1,7 +1,9 @@
|
|
| 1 |
import streamlit as st
|
| 2 |
import wisdom_extract
|
|
|
|
| 3 |
|
| 4 |
-
st.markdown(
|
|
|
|
| 5 |
<style>
|
| 6 |
body, html {
|
| 7 |
direction: RTL;
|
|
@@ -13,6 +15,10 @@ p, div, input, label, h1, h2, h3, h4, h5, h6 {
|
|
| 13 |
# unicode-bidi: bidi-override;
|
| 14 |
# text-align: right;
|
| 15 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
</style>
|
| 17 |
""", unsafe_allow_html=True)
|
| 18 |
|
|
@@ -33,24 +39,53 @@ def closest_embedding(queries, wisdom):
|
|
| 33 |
def query_transform(query):
|
| 34 |
return wisdom_extract.query_transform(query)
|
| 35 |
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
with cols[0]:
|
| 52 |
-
st.
|
|
|
|
|
|
|
|
|
|
| 53 |
with cols[1]:
|
| 54 |
-
st.
|
| 55 |
-
with cols[
|
| 56 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import streamlit as st
|
| 2 |
import wisdom_extract
|
| 3 |
+
import garood
|
| 4 |
|
| 5 |
+
st.markdown(
|
| 6 |
+
"""
|
| 7 |
<style>
|
| 8 |
body, html {
|
| 9 |
direction: RTL;
|
|
|
|
| 15 |
# unicode-bidi: bidi-override;
|
| 16 |
# text-align: right;
|
| 17 |
}
|
| 18 |
+
code {
|
| 19 |
+
font-family: 'Courier New', monospace;
|
| 20 |
+
font-weight: bold;
|
| 21 |
+
}
|
| 22 |
</style>
|
| 23 |
""", unsafe_allow_html=True)
|
| 24 |
|
|
|
|
| 39 |
def query_transform(query):
|
| 40 |
return wisdom_extract.query_transform(query)
|
| 41 |
|
| 42 |
+
tabs = st.tabs(["ุจุญุซ", "ูุฒู", "ุฅุชู
ุงู
"])
|
| 43 |
+
|
| 44 |
+
with tabs[0]:
|
| 45 |
+
# READ INPUT
|
| 46 |
+
query = "ู
ุง ูุญูู ุณูู
ูุงู ุฎูุฑ ู
ู
ุง ูุญู ุญุฑุจูุงู"
|
| 47 |
+
query = st.text_input(
|
| 48 |
+
label="ุฅุจุญุซ ูู ุงูุดุนุฑ",
|
| 49 |
+
value=query,
|
| 50 |
+
)
|
| 51 |
+
# FIND MATCHES
|
| 52 |
+
table = []
|
| 53 |
+
for score, verse, reason in closest_embedding(
|
| 54 |
+
query_transform(query),
|
| 55 |
+
read_wisdom("sample/2.wis.txt"),
|
| 56 |
+
):
|
| 57 |
+
table.append([verse, f"{score * 100:.1f}%", reason])
|
| 58 |
+
for idx, val in enumerate(table[:7]):
|
| 59 |
+
verse, score, reason = val
|
| 60 |
+
cols = st.columns([1, 8, 1, 1, 1])
|
| 61 |
+
with cols[0]:
|
| 62 |
+
st.write(idx)
|
| 63 |
+
with cols[1]:
|
| 64 |
+
st.write(verse)
|
| 65 |
+
with cols[2]:
|
| 66 |
+
st.write(score)
|
| 67 |
+
with cols[3]:
|
| 68 |
+
st.markdown("", help=reason[0][1])
|
| 69 |
+
|
| 70 |
+
with tabs[1]:
|
| 71 |
+
BH = garood.config()['bahr']['kamil_1']
|
| 72 |
+
query = "ูู ุบุงุฏุฑ ุงูุดุนุฑุงุก ู
ู ู
ุชุฑุฏู
"
|
| 73 |
+
cols = st.columns([6, 3, 3])
|
| 74 |
with cols[0]:
|
| 75 |
+
query = st.text_input(
|
| 76 |
+
label="ูู
ุจูุฒู ุงูุดุทุฑ",
|
| 77 |
+
value=query,
|
| 78 |
+
)
|
| 79 |
with cols[1]:
|
| 80 |
+
st.selectbox("ุงูุจุญุฑ", ["ุงููุงู
ู"])
|
| 81 |
+
with cols[0]:
|
| 82 |
+
AR = wisdom_extract.allam("allam/shakl.txt", {"input": query}).strip()
|
| 83 |
+
st.code(f"{query}\n{AR}\n", language=None)
|
| 84 |
+
EN, HR = garood.en_gen_enhr(garood.ar_gen_en(AR))
|
| 85 |
+
c, s = garood.bh_gen_best(BH, EN, HR, True)
|
| 86 |
+
g = garood.state_to_str(s, EN)
|
| 87 |
+
st.code(f"{garood.en2ar(g)}\n{garood.g2v(g)}\n", language=None)
|
| 88 |
+
|
| 89 |
+
with tabs[2]:
|
| 90 |
+
st.header("An owl")
|
| 91 |
+
st.image("https://static.streamlit.io/examples/owl.jpg", width=200)
|
garood.gold
CHANGED
|
@@ -26,6 +26,8 @@
|
|
| 26 |
31 แธคL_LT_BฤR_แธZ_ZA_ฤRY_NFฤแนข_BแธคT_
|
| 27 |
ุนูุณูุฑุงู ุนูููููู ุทููุงุจููู ุงูุจูุฉู ู
ูุฎุฑูู
ู
|
| 28 |
38 GSRN_GLY_YแนฌLA_BKA_BNTM_แธชRM_
|
|
|
|
|
|
|
| 29 |
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃูุนูุฌู
|
| 30 |
-1 None
|
| 31 |
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃูุนู
|
|
|
|
| 26 |
31 แธคL_LT_BฤR_แธZ_ZA_ฤRY_NFฤแนข_BแธคT_
|
| 27 |
ุนูุณูุฑุงู ุนูููููู ุทููุงุจููู ุงูุจูุฉู ู
ูุฎุฑูู
ู
|
| 28 |
38 GSRN_GLY_YแนฌLA_BKA_BNTM_แธชRM_
|
| 29 |
+
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู
|
| 30 |
+
-1 None
|
| 31 |
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃูุนูุฌู
|
| 32 |
-1 None
|
| 33 |
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃูุนู
|
garood.py
CHANGED
|
@@ -20,6 +20,30 @@ def config():
|
|
| 20 |
_config = yaml.safe_load(file)
|
| 21 |
return _config
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
def ar_gen_en(ar):
|
| 24 |
print(ar)
|
| 25 |
ar2en = config()["harf"]["ar"]
|
|
@@ -213,12 +237,13 @@ if __name__ == "__main__":
|
|
| 213 |
ุฃูููููู ููุฃูููููุฑู ุจูุนูุฏู ุฃูู
ูู ุงููููููุซูู
ู
|
| 214 |
ุญููููุชู ุจูุฃูุฑูุถู ุงูุฒููุงุฆูุฑูููู ููุฃูุตูุจูุญูุชู
|
| 215 |
ุนูุณูุฑุงู ุนูููููู ุทููุงุจููู ุงูุจูุฉู ู
ูุฎุฑูู
ู
|
|
|
|
| 216 |
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃูุนูุฌู
|
| 217 |
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃูุนู
|
| 218 |
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃู
|
| 219 |
""".strip().split("\n")):
|
| 220 |
EN, HR = en_gen_enhr(ar_gen_en(AR))
|
| 221 |
-
c, s = bh_gen_best(BH, EN, HR, i==
|
| 222 |
garood = state_to_str(s, EN)
|
| 223 |
print(garood)
|
| 224 |
file.write(f"{AR}\n")
|
|
|
|
| 20 |
_config = yaml.safe_load(file)
|
| 21 |
return _config
|
| 22 |
|
| 23 |
+
def en2ar(en):
|
| 24 |
+
print(en)
|
| 25 |
+
ar2en = config()["harf"]["ar"]
|
| 26 |
+
rev = {v["en"]: k for k, v in ar2en.items()}
|
| 27 |
+
ans = []
|
| 28 |
+
for e in en:
|
| 29 |
+
if e == "_":
|
| 30 |
+
ans.append(" ")
|
| 31 |
+
elif e in rev:
|
| 32 |
+
ans.append(rev[e])
|
| 33 |
+
elif e == '#':
|
| 34 |
+
ans.append('?')
|
| 35 |
+
return "".join(ans)
|
| 36 |
+
|
| 37 |
+
def g2v(G):
|
| 38 |
+
ans = []
|
| 39 |
+
for g in G:
|
| 40 |
+
if g == '_':
|
| 41 |
+
del ans[-1]
|
| 42 |
+
ans.append(". ")
|
| 43 |
+
else:
|
| 44 |
+
ans.append("-")
|
| 45 |
+
return "".join(ans)
|
| 46 |
+
|
| 47 |
def ar_gen_en(ar):
|
| 48 |
print(ar)
|
| 49 |
ar2en = config()["harf"]["ar"]
|
|
|
|
| 237 |
ุฃูููููู ููุฃูููููุฑู ุจูุนูุฏู ุฃูู
ูู ุงููููููุซูู
ู
|
| 238 |
ุญููููุชู ุจูุฃูุฑูุถู ุงูุฒููุงุฆูุฑูููู ููุฃูุตูุจูุญูุชู
|
| 239 |
ุนูุณูุฑุงู ุนูููููู ุทููุงุจููู ุงูุจูุฉู ู
ูุฎุฑูู
ู
|
| 240 |
+
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู
|
| 241 |
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃูุนูุฌู
|
| 242 |
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃูุนู
|
| 243 |
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃู
|
| 244 |
""".strip().split("\n")):
|
| 245 |
EN, HR = en_gen_enhr(ar_gen_en(AR))
|
| 246 |
+
c, s = bh_gen_best(BH, EN, HR, i==13)
|
| 247 |
garood = state_to_str(s, EN)
|
| 248 |
print(garood)
|
| 249 |
file.write(f"{AR}\n")
|
garood.tmp
CHANGED
|
@@ -1,44 +1,12 @@
|
|
| 1 |
-
ูููู ุบูุงุฏูุฑู ุงูุดููุนูุฑูุงุกู ู
ููู ู
ูุชูุฑูุฏ
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
HL_ฤ A_DRล _ล GRA_ฤMN_MTRD_DM#_
|
| 3 |
-
ุฃูู
ู ูููู ุนูุฑูููุชู ุงูุฏููุงุฑู ุจูุนูุฏู ุชููููููู
ู
|
| 4 |
-
ฤM_HL_GRF_TD_DA_RBG_DTWH_HM#_
|
| 5 |
-
ุฃูุนูููุงูู ุฑูุณูู
ู ุงูุฏููุงุฑู ููู
ู ููุชููููููู
ู
|
| 6 |
-
ฤG_YA_KRS_MD_DA_RLM_YTKL_LM#_
|
| 7 |
-
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃูุนูุฌูู
ู
|
| 8 |
-
แธคT_TA_TKL_LMKL_ฤแนขM_ML_ฤG_JM#_
|
| 9 |
-
ููุง ุฏูุงุฑู ุนููุจููููุฉู ุจูุงููุฌููููุงุกู ุชููููููู
ู
|
| 10 |
-
YA_DA_RGB_LTBL_JWA_ฤTKL_LMY_
|
| 11 |
-
ููุนูู
ูู ุตูุจูุงุญุงู ุฏูุงุฑู ุนููุจููููุฉู ููุงุณูููููู
ู
|
| 12 |
-
WGMY_แนขBA_แธคN_DA_RGB_LTWS_LMY_
|
| 13 |
-
ูููููููููุชู ููููููุง ููุงููุชูู ููููุฃููููููุง
|
| 14 |
-
FWQF_TFY_HA_NA_QTY_WKฤN_NHA_
|
| 15 |
-
ููุฏููู ููุฃูููุถููู ุญูุงุฌูุฉู ุงููู
ูุชููููููู
ู
|
| 16 |
-
FDNN_LฤQ_แธYแธคA_JTL_MTLW_WM#_
|
| 17 |
-
ููุชูุญูููู ุนูุจูููุฉู ุจูุงููุฌููุงุกู ููุฃูููููููุง
|
| 18 |
-
WTแธคL_LGB_LTBL_JWA_ฤWฤH_LNA_
|
| 19 |
-
ุจูุงููุญูุฒููู ููุงูุตููู
ููุงูู ููุงููู
ูุชูุซููููู
ู
|
| 20 |
-
BL_แธคZ_NFแนข_แนขM_MA_NFL_MTแนฎL_LM#_
|
| 21 |
-
ุญููููููุชู ู
ูู ุทููููู ุชููุงุฏูู
ู ุนููุฏููู
|
| 22 |
-
แธคY_YY_TMN_แนฌLLN_TQA_DMGH_DH#_
|
| 23 |
-
ุฃูููููู ููุฃูููููุฑู ุจูุนูุฏู ุฃูู
ูู ุงููููููุซูู
ู
|
| 24 |
-
ฤQ_WA_WฤQ_FRBG_DฤM_ML_HY_แนฎM#_
|
| 25 |
-
ุญููููุชู ุจูุฃูุฑูุถู ุงูุฒููุงุฆูุฑูููู ููุฃูุตูุจูุญูุชู
|
| 26 |
-
a_x_ia_ixx_xxiixaaa_aa_
|
| 27 |
-
แธคLLTBฤRแธALZZAฤRYNFฤแนขBแธคT
|
| 28 |
-
31 แธคL_LT_BฤR_แธZ_ZA_ฤRY_NFฤแนข_BแธคT_
|
| 29 |
-
35 แธคLLT_BฤR_แธZ_ZA_ฤRY_NFฤแนข_BแธคT_
|
| 30 |
-
35 แธคL_LT_BฤR_แธZZA_ฤRY_NFฤแนข_BแธคT_
|
| 31 |
-
35 แธคL_LT_BฤR_แธZ_ZA_ฤRY_NF_ฤแนข_BแธคT_
|
| 32 |
-
39 แธคLLT_BฤR_แธZZA_ฤRY_NFฤแนข_BแธคT_
|
| 33 |
-
39 แธคLLT_BฤR_แธZ_ZA_ฤRY_NF_ฤแนข_BแธคT_
|
| 34 |
-
39 แธคL_LT_BฤR_แธZZA_ฤRY_NF_ฤแนข_BแธคT_
|
| 35 |
-
43 แธคLLT_BฤR_แธZZA_ฤRY_NF_ฤแนข_BแธคT_
|
| 36 |
-
แธคL_LT_BฤR_แธZ_ZA_ฤRY_NFฤแนข_BแธคT_
|
| 37 |
-
ุนูุณูุฑุงู ุนูููููู ุทููุงุจููู ุงูุจูุฉู ู
ูุฎุฑูู
ู
|
| 38 |
-
GSRN_GLY_YแนฌLA_BKA_BNTM_แธชRM_
|
| 39 |
-
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃูุนูุฌู
|
| 40 |
-
None
|
| 41 |
-
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃูุนู
|
| 42 |
-
None
|
| 43 |
-
ุญูุชููู ุชููููููู
ู ููุงููุฃูุตูู
ูู ุงููุฃู
|
| 44 |
-
None
|
|
|
|
| 1 |
+
ูููู ุบูุงุฏูุฑู ุงูุดููุนูุฑูุงุกู ู
ููู ู
ูุชูุฑูุฏููู
ู
|
| 2 |
+
a_axaaxx_xaaxoi_oaa_xi
|
| 3 |
+
HLฤ ADRALล ล GRAฤMNMTRDDM
|
| 4 |
+
32 HL_ฤ A_DRล _ล GRA_ฤMN_MTRD_DM#_
|
| 5 |
+
36 HLฤ A_DRล _ล GRA_ฤMN_MTRD_DM#_
|
| 6 |
+
36 HL_ฤ A_DRล _ล GRA_ฤMN_MT_RD_DM#_
|
| 7 |
+
36 HL_ฤ A_DRล _ล G_RA_ฤMN_MTRD_DM#_
|
| 8 |
+
40 HLฤ A_DRล _ล GRA_ฤMN_MT_RD_DM#_
|
| 9 |
+
40 HLฤ A_DRล _ล G_RA_ฤMN_MTRD_DM#_
|
| 10 |
+
40 HL_ฤ A_DRล _ล G_RA_ฤMN_MT_RD_DM#_
|
| 11 |
+
44 HLฤ A_DRล _ล G_RA_ฤMN_MT_RD_DM#_
|
| 12 |
HL_ฤ A_DRล _ล GRA_ฤMN_MTRD_DM#_
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
garood.yaml
CHANGED
|
@@ -43,20 +43,20 @@ harf:
|
|
| 43 |
en: ฤ
|
| 44 |
ุฅ:
|
| 45 |
en: ฤ
|
| 46 |
-
ุก:
|
| 47 |
-
en: ฤ
|
| 48 |
ุฆ:
|
| 49 |
en: ฤ
|
| 50 |
ุค:
|
| 51 |
en: ฤ
|
|
|
|
|
|
|
| 52 |
|
| 53 |
# CONSONANTS
|
| 54 |
ุจ:
|
| 55 |
en: B
|
| 56 |
-
ุช:
|
| 57 |
-
en: T
|
| 58 |
ุฉ:
|
| 59 |
en: T
|
|
|
|
|
|
|
| 60 |
ุซ:
|
| 61 |
en: แนฎ
|
| 62 |
ุฌ:
|
|
|
|
| 43 |
en: ฤ
|
| 44 |
ุฅ:
|
| 45 |
en: ฤ
|
|
|
|
|
|
|
| 46 |
ุฆ:
|
| 47 |
en: ฤ
|
| 48 |
ุค:
|
| 49 |
en: ฤ
|
| 50 |
+
ุก:
|
| 51 |
+
en: ฤ
|
| 52 |
|
| 53 |
# CONSONANTS
|
| 54 |
ุจ:
|
| 55 |
en: B
|
|
|
|
|
|
|
| 56 |
ุฉ:
|
| 57 |
en: T
|
| 58 |
+
ุช:
|
| 59 |
+
en: T
|
| 60 |
ุซ:
|
| 61 |
en: แนฎ
|
| 62 |
ุฌ:
|