Union regexps and put it into separate file

FormalLanguageConstrainedPathQuerying · May 6, 2024 · ff9f4d4 · ff9f4d4
1 parent dd9f667
commit ff9f4d4
Show file tree

Hide file tree

Showing 10 changed files with 140 additions and 159 deletions.
diff --git a/tests/autotests/constants.py b/tests/autotests/constants.py
@@ -1,141 +1,5 @@
-from pyformlang.cfg import cfg
-
 LABEL: str = "label"
 IS_FINAL: str = "is_final"
 IS_START: str = "is_start"
 
 LABELS: list[str] = ["a", "b", "c", "d", "e", "f", "g", "h"]
-
-REGEX_SIMPLE: list[str] = [
-    "(aa)*",
-    "a | a",
-    "a* | a",
-    "(ab) | (ac)",
-    "(ab) | (abc)",
-    "(abd) | (abc)",
-    "(abd*) | (abc*)",
-    "(abd)* | (abc)*",
-    "((abd) | (abc))*",
-    "a*a*",
-    "a*a*b",
-    "a* | (a | b)*",
-    "a*(a | b)*",
-    "(a | c)*(a | b)*",
-]
-REGEX_TUPLE: list[tuple[str, str]] = [
-    ("a", "b"),
-    ("a", "a"),
-    ("a*", "a"),
-    ("a*", "aa"),
-    ("a*", "a*"),
-    ("(aa)*", "a*"),
-    ("(a|b)*", "a*"),
-    ("(a|b)*", "b"),
-    ("(a|b)*", "bbb"),
-    ("a|b", "a"),
-    ("a|b", "a|c"),
-    ("(a|b)(c|d)", "(a|c)(b|d)"),
-    ("(a|b)*", "(a|c)*"),
-    ("a*b*", "(a|b)*"),
-    ("(ab)*", "(a|b)*"),
-]
-QUERIES: list[str] = [
-    "a",
-    "a*",
-    "ab",
-    "abc",
-    "abcd",
-    "a*b*",
-    "(ab)*",
-    "ab*",
-    "ab*c*",
-    "ab*c",
-    "abc*",
-    "(a|b|c|d|e)*",
-    "(a|b|c|d|e)(a|b|c|d|e)*",
-    "(a|b|c|d|e)f*",
-    "(a|b)*",
-    "(a|b)*(c|d)*",
-    "(a | b)*(c | d)*(e | f)*",
-    "(a | b | c)*(d | e | f)*",
-    "((a|b)*c)*",
-    "((a | b) * c)*(d | e)",
-    "((a | b)*c)*((d | e)*f)*",
-]
-
-REGEXP_CFG: dict[str, list[cfg.CFG]] = {
-    "a": [cfg.CFG.from_text("S -> a"), cfg.CFG.from_text("S -> N B\nB -> $\nN -> a")],
-    "a*": [
-        cfg.CFG.from_text("S -> $ | a S"),
-        cfg.CFG.from_text("S -> $ | S S | a"),
-        cfg.CFG.from_text("S -> S a S | $"),
-    ],
-    "a b c": [cfg.CFG.from_text("S -> a b c"), cfg.CFG.from_text("S -> a B\nB -> b c")],
-    "a*b*": [
-        cfg.CFG.from_text("S -> S1 S2\nS2 -> $ | b S2\nS1 -> $ | a S1"),
-        cfg.CFG.from_text("S -> $ | S1 | a S\nS1 -> $ | b S1"),
-    ],
-    "(a b)*": [
-        cfg.CFG.from_text("S -> $ | a b S"),
-        cfg.CFG.from_text("S -> $ | S S1\nS1 -> a b"),
-    ],
-    "a b*c*": [
-        cfg.CFG.from_text("S -> S1 S2 S3\nS1 -> a\nS2 -> $ | S2 b\nS3 -> $ | c S3"),
-        cfg.CFG.from_text("S -> a S2 S3\nS2 -> S2 b | $\nS3 -> c | $ | S3 S3"),
-    ],
-    "(a|b|c|d|e)*": [
-        cfg.CFG.from_text("S -> $ | S1 S\nS1 -> a | b | c | d | e"),
-        cfg.CFG.from_text("S -> $ | a | b | c | d | e | S S"),
-        cfg.CFG.from_text("S -> $ | a S | b S | c S | e S | d S"),
-    ],
-    "((a | b) * c)*(d | e)": [
-        cfg.CFG.from_text(
-            "S -> S1 S2\nS1 -> S1 S1 | $ | S3 c\n S2 -> d | e\n S3 -> b S3 | $ | a S3"
-        ),
-        cfg.CFG.from_text("S -> S1 d | S1 e\nS1 -> S1 S3 c | $\nS3 -> b S3 | $ | a S3"),
-    ],
-}
-GRAMMARS: list[list[cfg.CFG]] = [
-    [
-        cfg.CFG.from_text("S -> $ | a S b | S S"),
-        cfg.CFG.from_text("S -> $ | a S b S"),
-        cfg.CFG.from_text("S -> $ | S a S b"),
-        cfg.CFG.from_text("S -> $ | a S b | S S S"),
-    ],
-    [
-        cfg.CFG.from_text("S -> $ | a S b | c S d | S S"),
-        cfg.CFG.from_text("S -> $ | a S b S | c S d S"),
-        cfg.CFG.from_text("S -> $ | S a S b | S c S d"),
-        cfg.CFG.from_text("S -> $ | a S b | c S d S | S S S"),
-    ],
-    [
-        cfg.CFG.from_text("S -> $ | S1 S S2\nS1 -> a | c\n S2 -> b | d\n S -> S S"),
-        cfg.CFG.from_text("S -> $ | S1 S S2 S\n S1 -> a | c\nS2 -> b | d"),
-        cfg.CFG.from_text("S -> $ | S a S b | S a S d | S c S d | S c S b"),
-        cfg.CFG.from_text("S -> $ | S1 S S2 | S S S\nS1 -> a | c\nS2-> b | d"),
-    ],
-    [
-        cfg.CFG.from_text("S -> S S | Se S1 Se\nSe -> $ | Se e\nS1 -> $ | a S1 b"),
-        cfg.CFG.from_text("S -> S1 | S S | e\nS1 -> $ | a S1 b"),
-        cfg.CFG.from_text("S -> S2 S | $\n S2 -> e | S1\n S1 -> $ | a S1 b"),
-        cfg.CFG.from_text("S -> $ | S1 S | e S\n S1 -> $ | a S1 b"),
-    ],
-    [
-        cfg.CFG.from_text("S -> a S | $"),
-        cfg.CFG.from_text("S -> S1 | a\nS1 -> a S1 | $"),
-    ],
-]
-GRAMMARS_DIFFERENT: list[cfg.CFG] = [
-    cfg.CFG.from_text(
-        "S -> S1 | S2\nS1 -> Sab | S1 c\nSab -> $ | a Sab b\nS2 -> Sbc | a S2\nSbc -> b Sbc c"
-    ),
-    cfg.CFG.from_text("S -> a | b | S c S | S d S | e S f | g S"),
-    cfg.CFG.from_text("S -> $ | a S b | b S a | e S f | S S | c S d | f S c | f S e"),
-]
-EBNF_GRAMMARS: list[str] = [
-    """S -> ( Sab c* ) | ( a* Sbc )
-    Sab -> a ( Sab | $ ) b
-    Sbc -> b ( Sbc | $ ) c""",
-    "S -> a | b | (S ( c | d ) S ) | ( e S f ) | ( g S )",
-    "S -> ( ( a S b ) | ( b S a ) | ( c S d ) | ( d S c ) | ( e S f ) | (f S e) )*",
-]
diff --git a/tests/autotests/grammars_constants.py b/tests/autotests/grammars_constants.py
@@ -0,0 +1,78 @@
+from pyformlang.cfg import cfg
+
+REGEXP_CFG: dict[str, list[cfg.CFG]] = {
+    "a": [cfg.CFG.from_text("S -> a"), cfg.CFG.from_text("S -> N B\nB -> $\nN -> a")],
+    "a*": [
+        cfg.CFG.from_text("S -> $ | a S"),
+        cfg.CFG.from_text("S -> $ | S S | a"),
+        cfg.CFG.from_text("S -> S a S | $"),
+    ],
+    "a b c": [cfg.CFG.from_text("S -> a b c"), cfg.CFG.from_text("S -> a B\nB -> b c")],
+    "a*b*": [
+        cfg.CFG.from_text("S -> S1 S2\nS2 -> $ | b S2\nS1 -> $ | a S1"),
+        cfg.CFG.from_text("S -> $ | S1 | a S\nS1 -> $ | b S1"),
+    ],
+    "(a b)*": [
+        cfg.CFG.from_text("S -> $ | a b S"),
+        cfg.CFG.from_text("S -> $ | S S1\nS1 -> a b"),
+    ],
+    "a b*c*": [
+        cfg.CFG.from_text("S -> S1 S2 S3\nS1 -> a\nS2 -> $ | S2 b\nS3 -> $ | c S3"),
+        cfg.CFG.from_text("S -> a S2 S3\nS2 -> S2 b | $\nS3 -> c | $ | S3 S3"),
+    ],
+    "(a|b|c|d|e)*": [
+        cfg.CFG.from_text("S -> $ | S1 S\nS1 -> a | b | c | d | e"),
+        cfg.CFG.from_text("S -> $ | a | b | c | d | e | S S"),
+        cfg.CFG.from_text("S -> $ | a S | b S | c S | e S | d S"),
+    ],
+    "((a | b) * c)*(d | e)": [
+        cfg.CFG.from_text(
+            "S -> S1 S2\nS1 -> S1 S1 | $ | S3 c\n S2 -> d | e\n S3 -> b S3 | $ | a S3"
+        ),
+        cfg.CFG.from_text("S -> S1 d | S1 e\nS1 -> S1 S3 c | $\nS3 -> b S3 | $ | a S3"),
+    ],
+}
+GRAMMARS: list[list[cfg.CFG]] = [
+    [
+        cfg.CFG.from_text("S -> $ | a S b | S S"),
+        cfg.CFG.from_text("S -> $ | a S b S"),
+        cfg.CFG.from_text("S -> $ | S a S b"),
+        cfg.CFG.from_text("S -> $ | a S b | S S S"),
+    ],
+    [
+        cfg.CFG.from_text("S -> $ | a S b | c S d | S S"),
+        cfg.CFG.from_text("S -> $ | a S b S | c S d S"),
+        cfg.CFG.from_text("S -> $ | S a S b | S c S d"),
+        cfg.CFG.from_text("S -> $ | a S b | c S d S | S S S"),
+    ],
+    [
+        cfg.CFG.from_text("S -> $ | S1 S S2\nS1 -> a | c\n S2 -> b | d\n S -> S S"),
+        cfg.CFG.from_text("S -> $ | S1 S S2 S\n S1 -> a | c\nS2 -> b | d"),
+        cfg.CFG.from_text("S -> $ | S a S b | S a S d | S c S d | S c S b"),
+        cfg.CFG.from_text("S -> $ | S1 S S2 | S S S\nS1 -> a | c\nS2-> b | d"),
+    ],
+    [
+        cfg.CFG.from_text("S -> S S | Se S1 Se\nSe -> $ | Se e\nS1 -> $ | a S1 b"),
+        cfg.CFG.from_text("S -> S1 | S S | e\nS1 -> $ | a S1 b"),
+        cfg.CFG.from_text("S -> S2 S | $\n S2 -> e | S1\n S1 -> $ | a S1 b"),
+        cfg.CFG.from_text("S -> $ | S1 S | e S\n S1 -> $ | a S1 b"),
+    ],
+    [
+        cfg.CFG.from_text("S -> a S | $"),
+        cfg.CFG.from_text("S -> S1 | a\nS1 -> a S1 | $"),
+    ],
+]
+GRAMMARS_DIFFERENT: list[cfg.CFG] = [
+    cfg.CFG.from_text(
+        "S -> S1 | S2\nS1 -> Sab | S1 c\nSab -> $ | a Sab b\nS2 -> Sbc | a S2\nSbc -> b Sbc c"
+    ),
+    cfg.CFG.from_text("S -> a | b | S c S | S d S | e S f | g S"),
+    cfg.CFG.from_text("S -> $ | a S b | b S a | e S f | S S | c S d | f S c | f S e"),
+]
+EBNF_GRAMMARS: list[str] = [
+    """S -> ( Sab c* ) | ( a* Sbc )
+    Sab -> a ( Sab | $ ) b
+    Sbc -> b ( Sbc | $ ) c""",
+    "S -> a | b | (S ( c | d ) S ) | ( e S f ) | ( g S )",
+    "S -> ( ( a S b ) | ( b S a ) | ( c S d ) | ( d S c ) | ( e S f ) | (f S e) )*",
+]
diff --git a/tests/autotests/regex_constants.py b/tests/autotests/regex_constants.py
@@ -0,0 +1,43 @@
+REGEXES = [
+    "(abd*) | (abc*)",
+    "(ab)*",
+    "a*a*",
+    "bbb",
+    "(a | b | c)*(d | e | f)*",
+    "a | a",
+    "(ab) | (ac)",
+    "abc*",
+    "abc",
+    "(abd) | (abc)",
+    "a* | (a | b)*",
+    "(a|b|c|d|e)(a|b|c|d|e)*",
+    "(a|b)*(c|d)*",
+    "(a|b)*",
+    "a* | a",
+    "(a|b|c|d|e)f*",
+    "aa",
+    "ab*",
+    "ab",
+    "ab*c*",
+    "(ab) | (abc)",
+    "a|c",
+    "(a|c)(b|d)",
+    "b",
+    "a",
+    "a*a*b",
+    "((a | b)*c)*((d | e)*f)*",
+    "((abd) | (abc))*",
+    "(a|c)*",
+    "((a | b) * c)*(d | e)",
+    "a*b*",
+    "(a | c)*(a | b)*",
+    "(a | b)*(c | d)*(e | f)*",
+    "a*(a | b)*",
+    "(abd)* | (abc)*",
+    "ab*c",
+    "(aa)*",
+    "a*",
+    "(a|b|c|d|e)*",
+    "((a|b)*c)*",
+    "abcd",
+]
diff --git a/tests/autotests/test_task2.py b/tests/autotests/test_task2.py
@@ -8,9 +8,10 @@
 import pytest
 import random
 import itertools
-from helper import GraphWordsHelper, generate_rnd_graph, generate_rnd_start_and_final
-from constants import IS_FINAL, IS_START, REGEX_SIMPLE
+from helper import GraphWordsHelper, generate_rnd_start_and_final
+from constants import IS_FINAL, IS_START
 from fixtures import small_graph
+from regex_constants import REGEXES
 
 # Fix import statements in try block to run tests
 try:
@@ -20,7 +21,7 @@
 
 
 class TestRegexToDfa:
-    @pytest.mark.parametrize("regex_str", REGEX_SIMPLE)
+    @pytest.mark.parametrize("regex_str", REGEXES)
     def test(self, regex_str: str) -> None:
         regex = Regex(regex_str)
         regex_cfg = regex.to_cfg()

diff --git a/tests/autotests/test_task3.py b/tests/autotests/test_task3.py
@@ -7,7 +7,7 @@
 import pytest
 import random
 import itertools
-from constants import REGEX_TUPLE
+from regex_constants import REGEXES
 
 # Fix import statements in try block to run tests
 try:
@@ -18,7 +18,9 @@
 
 
 class TestIntersect:
-    @pytest.mark.parametrize("regex_str1, regex_str2", REGEX_TUPLE)
+    @pytest.mark.parametrize(
+        "regex_str1, regex_str2", itertools.combinations(REGEXES, 2)
+    )
     def test(self, regex_str1: str, regex_str2: str) -> None:
         dfa1 = FiniteAutomaton(regex_to_dfa(regex_str1))
         dfa2 = FiniteAutomaton(regex_to_dfa(regex_str2))

diff --git a/tests/autotests/test_task4.py b/tests/autotests/test_task4.py
@@ -5,8 +5,7 @@
 import random
 from copy import deepcopy
 import pytest
-from networkx import MultiDiGraph
-from constants import QUERIES, LABELS
+from regex_constants import REGEXES
 from helper import generate_rnd_start_and_final
 from fixtures import graph
 
@@ -21,7 +20,7 @@
 
 @pytest.fixture(scope="class", params=range(5))
 def query(request) -> str:
-    return random.choice(QUERIES)
+    return random.choice(REGEXES)
 
 
 class TestReachability:

diff --git a/tests/autotests/test_task6.py b/tests/autotests/test_task6.py
@@ -4,7 +4,7 @@
 # Otherwise, please report it
 import itertools
 import pytest
-from constants import REGEXP_CFG, GRAMMARS
+from grammars_constants import REGEXP_CFG, GRAMMARS
 from rpq_template_test import rpq_cfpq_test, different_grammars_test
 from fixtures import graph
 

diff --git a/tests/autotests/test_task7.py b/tests/autotests/test_task7.py
@@ -5,7 +5,7 @@
 import itertools
 from copy import deepcopy
 import pytest
-from constants import REGEXP_CFG, GRAMMARS, GRAMMARS_DIFFERENT
+from grammars_constants import REGEXP_CFG, GRAMMARS, GRAMMARS_DIFFERENT
 from helper import generate_rnd_start_and_final
 from rpq_template_test import rpq_cfpq_test, different_grammars_test
 from fixtures import graph

diff --git a/tests/autotests/test_task8.py b/tests/autotests/test_task8.py
@@ -5,7 +5,7 @@
 import itertools
 from copy import deepcopy
 import pytest
-from constants import REGEXP_CFG, GRAMMARS, GRAMMARS_DIFFERENT, EBNF_GRAMMARS
+from grammars_constants import REGEXP_CFG, GRAMMARS, GRAMMARS_DIFFERENT, EBNF_GRAMMARS
 from helper import generate_rnd_start_and_final
 from rpq_template_test import rpq_cfpq_test, different_grammars_test
 from fixtures import graph