Merge pull request #61 from python-parsy/until_method_rebased

Added method 'until'

Author: spookylukey

RELEASE.rst

@@ -19,7 +19,7 @@ How to do releases
 
 * Release to PyPI::
 
-    $ ./release.sh 
+    $ ./release.sh
 
 
 Post release

docs/Makefile

@@ -17,4 +17,4 @@ help:
 # Catch-all target: route all unknown targets to Sphinx using the new
 # "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
 %: Makefile
-	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/history.rst

@@ -8,6 +8,7 @@ History and release notes
 ----------------
 
 * Dropped support for Python < 3.6
+* Added :meth:`Parsy.until`. Thanks `@mcdeoliveira <https://github.com/mcdeoliveira>`_!
 
 1.4.0 - 2021-11-15
 ------------------

docs/ref/methods_and_combinators.rst

@@ -111,6 +111,25 @@ can be used and manipulated as below.
       Returns a parser that expects the initial parser at least ``n`` times, and
       produces a list of the results.
 
+   .. method:: until(other_parser, [min=0, max=inf, consume_other=False])
+
+      Returns a parser that expects the initial parser followed by ``other_parser``.
+      The initial parser is expected at least ``min`` times and at most ``max`` times.
+      By default, it does not consume ``other_parser`` and it produces a list of the
+      results excluding ``other_parser``. If ``consume_other`` is ``True`` then
+      ``other_parser`` is consumed and its result is included in the list of results.
+
+      .. code:: python
+
+         >>> seq(string('A').until(string('B')), string('BC')).parse('AAABC')
+         [['A','A','A'], 'BC']
+         >>> string('A').until(string('B')).then(string('BC')).parse('AAABC')
+         'BC'
+         >>> string('A').until(string('BC'), consume_other=True).parse('AAABC')
+         ['A', 'A', 'A', 'BC']
+
+   .. versionadded:: 2.0
+
    .. method:: optional()
 
       Returns a parser that expects the initial parser zero or once, and maps

src/parsy/__init__.py

@@ -181,6 +181,43 @@ def at_least(self, n):
     def optional(self):
         return self.times(0, 1).map(lambda v: v[0] if v else None)
 
+    def until(self, other, min=0, max=float("inf"), consume_other=False):
+        @Parser
+        def until_parser(stream, index):
+            values = []
+            times = 0
+            while True:
+
+                # try parser first
+                res = other(stream, index)
+                if res.status and times >= min:
+                    if consume_other:
+                        # consume other
+                        values.append(res.value)
+                        index = res.index
+                    return Result.success(index, values)
+
+                # exceeded max?
+                if times >= max:
+                    # return failure, it matched parser more than max times
+                    return Result.failure(index, f"at most {max} items")
+
+                # failed, try parser
+                result = self(stream, index)
+                if result.status:
+                    # consume
+                    values.append(result.value)
+                    index = result.index
+                    times += 1
+                elif times >= min:
+                    # return failure, parser is not followed by other
+                    return Result.failure(index, "did not find other parser")
+                else:
+                    # return failure, it did not match parser at least min times
+                    return Result.failure(index, f"at least {min} items; got {times} item(s)")
+
+        return until_parser
+
     def sep_by(self, sep, *, min=0, max=float("inf")):
         zero_times = success([])
         if max == 0:

tests/test_parsy.py

@@ -347,6 +347,73 @@ def test_at_most(self):
         self.assertEqual(ab.at_most(2).parse("abab"), ["ab", "ab"])
         self.assertRaises(ParseError, ab.at_most(2).parse, "ababab")
 
+    def test_until(self):
+
+        until = string("s").until(string("x"))
+
+        s = "ssssx"
+        self.assertEqual(until.parse_partial(s), (4 * ["s"], "x"))
+        self.assertEqual(seq(until, string("x")).parse(s), [4 * ["s"], "x"])
+        self.assertEqual(until.then(string("x")).parse(s), "x")
+
+        s = "ssssxy"
+        self.assertEqual(until.parse_partial(s), (4 * ["s"], "xy"))
+        self.assertEqual(seq(until, string("x")).parse_partial(s), ([4 * ["s"], "x"], "y"))
+        self.assertEqual(until.then(string("x")).parse_partial(s), ("x", "y"))
+
+        self.assertRaises(ParseError, until.parse, "ssssy")
+        self.assertRaises(ParseError, until.parse, "xssssxy")
+
+        self.assertEqual(until.parse_partial("xxx"), ([], "xxx"))
+
+        until = regex(".").until(string("x"))
+        self.assertEqual(until.parse_partial("xxxx"), ([], "xxxx"))
+
+    def test_until_with_consume_other(self):
+
+        until = string("s").until(string("x"), consume_other=True)
+
+        self.assertEqual(until.parse("ssssx"), 4 * ["s"] + ["x"])
+        self.assertEqual(until.parse_partial("ssssxy"), (4 * ["s"] + ["x"], "y"))
+
+        self.assertEqual(until.parse_partial("xxx"), (["x"], "xx"))
+
+        self.assertRaises(ParseError, until.parse, "ssssy")
+        self.assertRaises(ParseError, until.parse, "xssssxy")
+
+    def test_until_with_min(self):
+
+        until = string("s").until(string("x"), min=3)
+
+        self.assertEqual(until.parse_partial("sssx"), (3 * ["s"], "x"))
+        self.assertEqual(until.parse_partial("sssssx"), (5 * ["s"], "x"))
+
+        self.assertRaises(ParseError, until.parse_partial, "ssx")
+
+    def test_until_with_max(self):
+
+        # until with max
+        until = string("s").until(string("x"), max=3)
+
+        self.assertEqual(until.parse_partial("ssx"), (2 * ["s"], "x"))
+        self.assertEqual(until.parse_partial("sssx"), (3 * ["s"], "x"))
+
+        self.assertRaises(ParseError, until.parse_partial, "ssssx")
+
+    def test_until_with_min_max(self):
+
+        until = string("s").until(string("x"), min=3, max=5)
+
+        self.assertEqual(until.parse_partial("sssx"), (3 * ["s"], "x"))
+        self.assertEqual(until.parse_partial("sssssx"), (5 * ["s"], "x"))
+
+        with self.assertRaises(ParseError) as cm:
+            until.parse_partial("ssx")
+        assert cm.exception.args[0] == frozenset({"at least 3 items; got 2 item(s)"})
+        with self.assertRaises(ParseError) as cm:
+            until.parse_partial("ssssssx")
+        assert cm.exception.args[0] == frozenset({"at most 5 items"})
+
     def test_optional(self):
         p = string("a").optional()
         self.assertEqual(p.parse("a"), "a")