initial commit

.gitignore

@@ -0,0 +1 @@
+.idea

TP1.py

@@ -0,0 +1,52 @@
+import re
+
+# ex 9
+mots = ['a', 'aab', 'aaab', 'aabaab', 'baabaab', 'abaabaaabaaaab']
+regExps = [r"aa*b", r'a(a|b)*', r'(aa*b)*', r'(a|aab)*', r'a*|aab*']
+
+for r in regExps:
+    print("Match for regex '" + r + "' are :")
+    for mot in mots:
+        m = re.fullmatch('(' + r + ')', mot)
+        if m:
+            print("  " + mot)
+
+
+# ex 11
+def say_hello(text):
+    regex = r'([a-zA-Z]+)\.[a-zA-Z]+@umons\.ac\.be'
+    m = re.search(regex, text)
+    if m:
+        print("Hello " + m.group(1))
+
+
+say_hello("jean.bob@umons.ac.be")
+say_hello("Patrick.BOUl@umons.ac.be")
+say_hello("s.ac.be")
+
+
+# ex 12
+def newlines(text,nbr):
+    regex = r'((\w+ ){'+str(nbr-1)+r'}\w+)|(\w+)'
+    m = re.findall(regex, text)
+    res = ""
+    if m:
+        for group in m:
+            mots = group[0].split(r" ")
+            if len(mots) == nbr:
+                for i in range(nbr):
+                    res += str(i+1) + ". " + mots[i] + "\t"
+                res += "\n"
+            else:
+                res += " "+group[2]
+
+    return res
+
+
+def newlines_with_varying_size(text, n=5):
+    pattern = r'\s+'.join(r'(\w+)' for _ in range(n))
+    group = [rf'{i}. \{i}' for i in range(1, n + 1)]
+    repl = '\t'.join(group) + '\n'
+    return re.sub(pattern, repl, text)
+
+print(newlines('cet exercice travaille avec une suite de mots', 4))

lark/test.py

@@ -0,0 +1,50 @@
+import sys
+from lark import Lark, Transformer
+
+json_grammar = r"""
+    ?value: dict
+          | list
+          | string
+          | SIGNED_NUMBER      -> number
+          | "true"             -> true
+          | "false"            -> false
+          | "null"             -> null
+
+    list : "[" [value ("," value)*] "]"
+
+    dict : "{" [pair ("," pair)*] "}"
+    pair : string ":" value
+
+    string : ESCAPED_STRING
+
+    %import common.ESCAPED_STRING
+    %import common.SIGNED_NUMBER
+    %import common.WS
+    %ignore WS
+    """
+
+
+class TreeToJson(Transformer):
+    def string(self, s):
+        (s,) = s
+        return s[1:-1]
+
+    def number(self, n):
+        (n,) = n
+        return float(n)
+
+    list = list
+    pair = tuple
+    dict = dict
+
+    null = lambda self, _: None
+    true = lambda self, _: True
+    false = lambda self, _: False
+
+
+json_parser = Lark(json_grammar, start='value', parser='lalr', transformer=TreeToJson())
+
+if __name__ == '__main__':
+    text = '{"key": ["item0", "item1", 3.14, true]}'
+    tree = json_parser.parse(text)
+    print(tree)

ply/example.py

@@ -0,0 +1,69 @@
+import ply.lex as lex
+
+tokens = (
+    'INTEGER',
+    'FLOAT',
+    'ADD_OP',
+    'MUL_OP',
+    'BRACKET',
+)
+
+def t_BRACKET(t):
+    r'\(|\)'
+    if t.value == '(':
+        t.value = "L"
+    else:
+        t.value = "R"
+    return t
+
+def t_MUL_OP(t):
+    r'\*|/'
+    return t
+
+
+def t_ADD_OP(t):
+    r'\+|-'
+    return t
+
+
+def t_FLOAT(t):
+    r'\d+\.\d*'
+    t.value = float(t.value)
+    return t
+
+def t_INTEGER(t):
+    r'\d+'
+    t.value = int(t.value)
+    return t
+
+
+def t_newline(t):
+    r'\n+'
+    t.lexer.lineno += len(t.value)
+
+
+t_ignore = ' |\t'
+
+
+def t_error(t):
+    print("Illegalcharacter '%s'" %t.value[0])
+    t.lexer.skip(1)
+
+
+if __name__ == "__main__":
+    import sys
+    lexer = lex.lex()
+    lexer.input(sys.stdin.read())
+    lb = 0
+    for token in lexer:
+        if token.type == "BRACKET":
+            if token.value == "L":
+                lb += 1
+            else:
+                lb -= 1
+            if lb < 0:
+                print("BRACKET missing")
+
+        print("line %d : %s (%s) " % (token.lineno, token.type, token.value))
+    if lb != 0:
+        print("BRACKET missing")

ply/example2.py

@@ -0,0 +1,50 @@
+import ply.lex as lex
+
+tokens = (
+    'COMMENTBEGIN',
+    'COMMENTEND',
+    'CODE',
+)
+
+states = (
+    ('inComment', 'inclusive'),
+)
+
+def t_inComment_COMMENTEND(t):
+    r'\*/'
+    t.lexer.begin('INITIAL')
+    return t
+
+def t_inComment_CODE(t):
+    r'.'
+    t.value = ''
+    return t
+
+def t_COMMENTBEGIN(t):
+    r'/\*'
+    t.lexer.begin('inComment')
+    return t
+
+t_CODE = r'.'
+
+def t_inComment_newline(t):
+    r'\n+'
+
+def t_newline(t) :
+    r'\n+'
+    t.lexer.lineno += len(t.value)
+
+if __name__ == "__main__" :
+    import sys
+    lexer = lex.lex()
+    lexer.input(sys.stdin.read())
+    ret = ""
+    lineno = 1
+
+    for token in lexer:
+        if token.lineno > lineno :
+            lineno += 1
+            ret += '\n'
+        if token.type == 'CODE' :
+            ret += token.value
+    print(ret)

ply/test.txt

@@ -0,0 +1,9 @@
+3+3
+00-0+12+++3
+3*4/5
+3.3
+4. 5+3
+%
+
+( 5. + 33)
+(())()()