Delete cc.py
Browse files
cc.py
DELETED
@@ -1,312 +0,0 @@
|
|
1 |
-
import copy
|
2 |
-
import streamlit as st
|
3 |
-
|
4 |
-
stateMap = {}
|
5 |
-
diction = {}
|
6 |
-
start_symbol = ""
|
7 |
-
rules = []
|
8 |
-
statesDict={}
|
9 |
-
stateCount = 0
|
10 |
-
separatedRulesList = []
|
11 |
-
|
12 |
-
def grammarAugmentation(rules, nonterm_userdef, start_symbol):
|
13 |
-
newRules = []
|
14 |
-
newChar = start_symbol + "'"
|
15 |
-
while (newChar in nonterm_userdef):
|
16 |
-
newChar += "'"
|
17 |
-
newRules.append([newChar, ['.', start_symbol]])
|
18 |
-
for rule in rules:
|
19 |
-
k = rule.split("->")
|
20 |
-
lhs = k[0].strip()
|
21 |
-
rhs = k[1].strip()
|
22 |
-
multirhs = rhs.split('|')
|
23 |
-
for rhs1 in multirhs:
|
24 |
-
rhs1 = rhs1.strip().split()
|
25 |
-
rhs1.insert(0, '.')
|
26 |
-
newRules.append([lhs, rhs1])
|
27 |
-
return newRules
|
28 |
-
|
29 |
-
def findClosure(input_state, dotSymbol):
|
30 |
-
global separatedRulesList
|
31 |
-
|
32 |
-
closureSet = []
|
33 |
-
|
34 |
-
if isinstance(input_state, int):
|
35 |
-
for rule in separatedRulesList:
|
36 |
-
if rule[0] == dotSymbol:
|
37 |
-
closureSet.append(rule)
|
38 |
-
else:
|
39 |
-
closureSet = input_state
|
40 |
-
|
41 |
-
prevLen = -1
|
42 |
-
while prevLen != len(closureSet):
|
43 |
-
prevLen = len(closureSet)
|
44 |
-
|
45 |
-
tempClosureSet = []
|
46 |
-
for rule in closureSet:
|
47 |
-
indexOfDot = rule[1].index('.')
|
48 |
-
if rule[1][-1] != '.':
|
49 |
-
dotPointsHere = rule[1][indexOfDot + 1]
|
50 |
-
for in_rule in separatedRulesList:
|
51 |
-
if dotPointsHere == in_rule[0] and in_rule not in tempClosureSet:
|
52 |
-
tempClosureSet.append(in_rule)
|
53 |
-
|
54 |
-
for rule in tempClosureSet:
|
55 |
-
if rule not in closureSet:
|
56 |
-
closureSet.append(rule)
|
57 |
-
return closureSet
|
58 |
-
|
59 |
-
def compute_GOTO(state):
|
60 |
-
global statesDict, stateCount
|
61 |
-
generateStatesFor = []
|
62 |
-
for rule in statesDict[state]:
|
63 |
-
if rule[1][-1] != '.':
|
64 |
-
indexOfDot = rule[1].index('.')
|
65 |
-
dotPointsHere = rule[1][indexOfDot + 1]
|
66 |
-
if dotPointsHere not in generateStatesFor:
|
67 |
-
generateStatesFor.append(dotPointsHere)
|
68 |
-
if len(generateStatesFor) != 0:
|
69 |
-
for symbol in generateStatesFor:
|
70 |
-
GOTO(state, symbol)
|
71 |
-
return
|
72 |
-
|
73 |
-
def GOTO(state, charNextToDot):
|
74 |
-
global statesDict, stateCount, stateMap
|
75 |
-
newState = []
|
76 |
-
for rule in statesDict[state]:
|
77 |
-
indexOfDot = rule[1].index('.')
|
78 |
-
if rule[1][-1] != '.':
|
79 |
-
if rule[1][indexOfDot + 1] == charNextToDot:
|
80 |
-
shiftedRule = copy.deepcopy(rule)
|
81 |
-
shiftedRule[1][indexOfDot] = shiftedRule[1][indexOfDot + 1]
|
82 |
-
shiftedRule[1][indexOfDot + 1] = '.'
|
83 |
-
newState.append(shiftedRule)
|
84 |
-
|
85 |
-
addClosureRules = []
|
86 |
-
for rule in newState:
|
87 |
-
indexDot = rule[1].index('.')
|
88 |
-
if rule[1][-1] != '.':
|
89 |
-
closureRes = findClosure(newState, rule[1][indexDot + 1])
|
90 |
-
for rule in closureRes:
|
91 |
-
if rule not in addClosureRules and rule not in newState:
|
92 |
-
addClosureRules.append(rule)
|
93 |
-
|
94 |
-
for rule in addClosureRules:
|
95 |
-
newState.append(rule)
|
96 |
-
|
97 |
-
stateExists = -1
|
98 |
-
for state_num in statesDict:
|
99 |
-
if statesDict[state_num] == newState:
|
100 |
-
stateExists = state_num
|
101 |
-
break
|
102 |
-
|
103 |
-
if stateExists == -1:
|
104 |
-
stateCount += 1
|
105 |
-
statesDict[stateCount] = newState
|
106 |
-
stateMap[(state, charNextToDot)] = stateCount
|
107 |
-
else:
|
108 |
-
stateMap[(state, charNextToDot)] = stateExists
|
109 |
-
return
|
110 |
-
|
111 |
-
def generateStates(I0):
|
112 |
-
global statesDict, stateCount
|
113 |
-
|
114 |
-
statesDict[0] = I0
|
115 |
-
stateCount = 0
|
116 |
-
prev_len = -1
|
117 |
-
called_GOTO_on = []
|
118 |
-
while (len(statesDict) != prev_len):
|
119 |
-
prev_len = len(statesDict)
|
120 |
-
keys = list(statesDict.keys())
|
121 |
-
for key in keys:
|
122 |
-
if key not in called_GOTO_on:
|
123 |
-
called_GOTO_on.append(key)
|
124 |
-
compute_GOTO(key)
|
125 |
-
return
|
126 |
-
|
127 |
-
def first(rule):
|
128 |
-
global diction, term_userdef
|
129 |
-
if len(rule) != 0 and (rule is not None):
|
130 |
-
if rule[0] in term_userdef:
|
131 |
-
return rule[0]
|
132 |
-
elif rule[0] == '#':
|
133 |
-
return '#'
|
134 |
-
if len(rule) != 0:
|
135 |
-
if rule[0] in list(diction.keys()):
|
136 |
-
fres = []
|
137 |
-
rhs_rules = diction[rule[0]]
|
138 |
-
for itr in rhs_rules:
|
139 |
-
indivRes = first(itr)
|
140 |
-
if type(indivRes) is list:
|
141 |
-
for i in indivRes:
|
142 |
-
fres.append(i)
|
143 |
-
else:
|
144 |
-
fres.append(indivRes)
|
145 |
-
|
146 |
-
if '#' not in fres:
|
147 |
-
return fres
|
148 |
-
else:
|
149 |
-
newList = []
|
150 |
-
fres.remove('#')
|
151 |
-
if len(rule) > 1:
|
152 |
-
ansNew = first(rule[1:])
|
153 |
-
if ansNew != None:
|
154 |
-
if type(ansNew) is list:
|
155 |
-
newList = fres + ansNew
|
156 |
-
else:
|
157 |
-
newList = fres + [ansNew]
|
158 |
-
else:
|
159 |
-
newList = fres
|
160 |
-
return newList
|
161 |
-
fres.append('#')
|
162 |
-
return fres
|
163 |
-
|
164 |
-
def follow(nt):
|
165 |
-
global start_symbol, diction
|
166 |
-
solset = set()
|
167 |
-
if nt == start_symbol:
|
168 |
-
solset.add('$')
|
169 |
-
for curNT in diction:
|
170 |
-
rhs = diction[curNT]
|
171 |
-
for subrule in rhs:
|
172 |
-
if nt in subrule:
|
173 |
-
while nt in subrule:
|
174 |
-
index_nt = subrule.index(nt)
|
175 |
-
subrule = subrule[index_nt + 1:]
|
176 |
-
if len(subrule) != 0:
|
177 |
-
res = first(subrule)
|
178 |
-
if '#' in res:
|
179 |
-
newList = []
|
180 |
-
res.remove('#')
|
181 |
-
ansNew = follow(curNT)
|
182 |
-
if ansNew != None:
|
183 |
-
if type(ansNew) is list:
|
184 |
-
newList = res + ansNew
|
185 |
-
else:
|
186 |
-
newList = res + [ansNew]
|
187 |
-
else:
|
188 |
-
newList = res
|
189 |
-
res = newList
|
190 |
-
else:
|
191 |
-
if nt != curNT:
|
192 |
-
res = follow(curNT)
|
193 |
-
|
194 |
-
if res is not None:
|
195 |
-
if type(res) is list:
|
196 |
-
for g in res:
|
197 |
-
solset.add(g)
|
198 |
-
else:
|
199 |
-
solset.add(res)
|
200 |
-
return list(solset)
|
201 |
-
|
202 |
-
def createParseTable(statesDict, stateMap, T, NT):
|
203 |
-
global separatedRulesList, diction
|
204 |
-
|
205 |
-
parse_table = {i: {} for i in range(len(statesDict))}
|
206 |
-
|
207 |
-
for (state, symbol) in stateMap:
|
208 |
-
if symbol in T:
|
209 |
-
parse_table[state][symbol] = f'S{stateMap[(state, symbol)]}'
|
210 |
-
elif symbol in NT:
|
211 |
-
parse_table[state][symbol] = str(stateMap[(state, symbol)])
|
212 |
-
|
213 |
-
for state in statesDict:
|
214 |
-
for item in statesDict[state]:
|
215 |
-
if item[1][-1] == '.':
|
216 |
-
prod = f"{item[0]} -> {' '.join(item[1][:-1])}"
|
217 |
-
|
218 |
-
if prod == f"{separatedRulesList[0][0]} -> {separatedRulesList[0][1][1]}":
|
219 |
-
parse_table[state]['$'] = 'ACC'
|
220 |
-
else:
|
221 |
-
rule_index = next(
|
222 |
-
(i for i, rule in enumerate(separatedRulesList) if rule == item),
|
223 |
-
None
|
224 |
-
)
|
225 |
-
|
226 |
-
if rule_index is None:
|
227 |
-
print(f"Warning: Rule for item {item} not found in separatedRulesList.")
|
228 |
-
continue
|
229 |
-
|
230 |
-
for symbol in T + ['$']:
|
231 |
-
if symbol not in parse_table[state]:
|
232 |
-
parse_table[state][symbol] = f'R{rule_index}'
|
233 |
-
|
234 |
-
return parse_table
|
235 |
-
|
236 |
-
|
237 |
-
def main():
|
238 |
-
st.title("SLR(1) Parser Generator")
|
239 |
-
|
240 |
-
st.header("Grammar Input")
|
241 |
-
rules = st.text_area("Enter the grammar rules (one per line):",
|
242 |
-
"E -> E + T | T\nT -> T * F | F\nF -> ( E ) | id")
|
243 |
-
rules = rules.split('\n')
|
244 |
-
|
245 |
-
nonterm_userdef = st.text_input("Enter the non-terminal symbols (separated by space):", "E T F")
|
246 |
-
nonterm_userdef = nonterm_userdef.split()
|
247 |
-
|
248 |
-
term_userdef = st.text_input("Enter the terminal symbols (separated by space):", "id + * ( )")
|
249 |
-
term_userdef = term_userdef.split()
|
250 |
-
|
251 |
-
start_symbol = st.text_input("Enter the start symbol:", "E")
|
252 |
-
|
253 |
-
if st.button("Generate SLR(1) Parser"):
|
254 |
-
st.subheader("Original Grammar Input:")
|
255 |
-
for rule in rules:
|
256 |
-
st.write(rule)
|
257 |
-
|
258 |
-
st.subheader("Grammar after Augmentation:")
|
259 |
-
global separatedRulesList
|
260 |
-
separatedRulesList = grammarAugmentation(rules, nonterm_userdef, start_symbol)
|
261 |
-
for rule in separatedRulesList:
|
262 |
-
st.write(f"{rule[0]} -> {' '.join(rule[1])}")
|
263 |
-
|
264 |
-
start_symbol = separatedRulesList[0][0]
|
265 |
-
st.subheader("Calculated Closure: I0")
|
266 |
-
I0 = findClosure(0, start_symbol)
|
267 |
-
|
268 |
-
st.write("I0:")
|
269 |
-
for rule in I0:
|
270 |
-
st.write(f"{rule[0]} -> {' '.join(rule[1])}")
|
271 |
-
|
272 |
-
generateStates(I0)
|
273 |
-
|
274 |
-
st.subheader("Generated States:")
|
275 |
-
for state, rules in statesDict.items():
|
276 |
-
st.write(f"I{state}:")
|
277 |
-
for rule in rules:
|
278 |
-
st.write(f" {rule[0]} -> {' '.join(rule[1])}")
|
279 |
-
st.write("")
|
280 |
-
|
281 |
-
st.subheader("SLR(1) Parsing Table")
|
282 |
-
table = createParseTable(statesDict, stateMap, term_userdef, nonterm_userdef)
|
283 |
-
|
284 |
-
cols = ['State'] + term_userdef + ['$'] + nonterm_userdef
|
285 |
-
table_data = []
|
286 |
-
for state in range(len(statesDict)):
|
287 |
-
row = [f'I{state}']
|
288 |
-
for symbol in term_userdef + ['$'] + nonterm_userdef:
|
289 |
-
row.append(table[state].get(symbol, ''))
|
290 |
-
table_data.append(row)
|
291 |
-
|
292 |
-
st.table([cols] + table_data)
|
293 |
-
|
294 |
-
compact_table = "State`" + '`'.join(term_userdef + ['$'] + nonterm_userdef) + '`'
|
295 |
-
for state in range(len(statesDict)):
|
296 |
-
compact_table += f"I{state}"
|
297 |
-
for symbol in term_userdef + ['$'] + nonterm_userdef:
|
298 |
-
compact_table += table[state].get(symbol, '')
|
299 |
-
st.subheader("Follow Sets")
|
300 |
-
follow_sets = {}
|
301 |
-
for nt in nonterm_userdef:
|
302 |
-
follow_set = follow(nt)
|
303 |
-
follow_sets[nt] = follow_set
|
304 |
-
st.write(f"Follow({nt}): {{ {' , '.join(follow_set)} }}")
|
305 |
-
compact_follow = "Non-Terminal`Follow Set\n"
|
306 |
-
for nt, follow_set in follow_sets.items():
|
307 |
-
compact_follow += f"{nt}`{{ {' , '.join(follow_set)} }}\n"
|
308 |
-
|
309 |
-
st.text_area("Compact Follow Sets Representation:", value=compact_follow, height=300)
|
310 |
-
|
311 |
-
if __name__ == "__main__":
|
312 |
-
main()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|