[PATCH 01 of 10 shelve-ext v4] scmutil: add a simple key-value file helper

[Kostia Balytskyi]

# HG changeset patch
# User Kostia Balytskyi <ikostia at fb.com>
# Date 1489185222 28800
#      Fri Mar 10 14:33:42 2017 -0800
# Node ID ca01391d61f5725c4fc79ccffe0c8e2d6dbb97f0
# Parent  2a1b16dbb9c4760002059d97c15cd0828fb1fb60
scmutil: add a simple key-value file helper

The purpose of the added class is to serve purposes like save files of shelve
or state files of shelve, rebase and histedit. Keys of these files can be
alphanumeric and start with letters, while values must not contain newlines.

In light of Mercurial's reluctancy to use Python's json module, this tries
to provide a reasonable alternative for a non-nested named data.
Comparing to current approach of storing state in plain text files, where
semantic meaning of lines of text is only determined by their oreder,
simple key-value file allows for reordering lines and thus helps handle
optional values.

Initial use-case I see for this is obs-shelve's shelve files. Later we
can possibly migrate state files to this approach.

The test is in a new file beause I did not figure out where to put it
within existing test suite. If you give me a better idea, I will gladly
follow it.

diff --git a/mercurial/scmutil.py b/mercurial/scmutil.py
--- a/mercurial/scmutil.py
+++ b/mercurial/scmutil.py
@@ -965,3 +965,41 @@ def gddeltaconfig(ui):
     """
     # experimental config: format.generaldelta
     return ui.configbool('format', 'generaldelta', False)
+
+class simplekeyvaluefile(object):
+    """A simple file with key=value lines
+
+    Keys must be alphanumerics and start with a letter, values must not
+    contain '\n' characters"""
+
+    def __init__(self, vfs, path, keys=None):
+        self.vfs = vfs
+        self.path = path
+
+    def read(self):
+        lines = self.vfs.readlines(self.path)
+        try:
+            d = dict(line[:-1].split('=', 1) for line in lines if line)
+        except ValueError as e:
+            raise error.CorruptedState(str(e))
+        return d
+
+    def write(self, data):
+        """Write key=>value mapping to a file
+        data is a dict. Keys must be alphanumerical and start with a letter.
+        Values must not contain newline characters."""
+        lines = []
+        for k, v in data.items():
+            if not k[0].isalpha():
+                e = "keys must start with a letter in a key-value file"
+                raise error.ProgrammingError(e)
+            if not k.isalnum():
+                e = "invalid key name in a simple key-value file"
+                raise error.ProgrammingError(e)
+            if '\n' in v:
+                e = "invalid value in a simple key-value file"
+                raise error.ProgrammingError(e)
+            lines.append("%s=%s\n" % (k, v))
+        with self.vfs(self.path, mode='wb', atomictemp=True) as fp:
+            fp.write(''.join(lines))
+
diff --git a/tests/test-simplekeyvaluefile.py b/tests/test-simplekeyvaluefile.py
new file mode 100644
--- /dev/null
+++ b/tests/test-simplekeyvaluefile.py
@@ -0,0 +1,72 @@
+from __future__ import absolute_import
+
+import unittest
+import silenttestrunner
+
+from mercurial import (
+    error,
+    scmutil,
+)
+
+class mockfile(object):
+    def __init__(self, name, fs):
+        self.name = name
+        self.fs = fs
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, *args, **kwargs):
+        pass
+
+    def write(self, text):
+        self.fs.contents[self.name] = text
+
+    def read(self):
+        return self.fs.contents[self.name]
+
+class mockvfs(object):
+    def __init__(self):
+        self.contents = {}
+
+    def read(self, path):
+        return mockfile(path, self).read()
+
+    def readlines(self, path):
+        return mockfile(path, self).read().split('\n')
+
+    def __call__(self, path, mode, atomictemp):
+        return mockfile(path, self)
+
+class testsimplekeyvaluefile(unittest.TestCase):
+    def setUp(self):
+        self.vfs = mockvfs()
+
+    def testbasicwriting(self):
+        d = {'key1': 'value1', 'Key2': 'value2'}
+        scmutil.simplekeyvaluefile(self.vfs, 'kvfile').write(d)
+        self.assertEqual(sorted(self.vfs.read('kvfile').split('\n')),
+                         ['', 'Key2=value2', 'key1=value1'])
+
+    def testinvalidkeys(self):
+        d = {'0key1': 'value1', 'Key2': 'value2'}
+        with self.assertRaisesRegexp(error.ProgrammingError,
+                                     "keys must start with a letter.*"):
+            scmutil.simplekeyvaluefile(self.vfs, 'kvfile').write(d)
+        d = {'key1@': 'value1', 'Key2': 'value2'}
+        with self.assertRaisesRegexp(error.ProgrammingError, "invalid key.*"):
+            scmutil.simplekeyvaluefile(self.vfs, 'kvfile').write(d)
+
+    def testinvalidvalues(self):
+        d = {'key1': 'value1', 'Key2': 'value2\n'}
+        with self.assertRaisesRegexp(error.ProgrammingError, "invalid val.*"):
+            scmutil.simplekeyvaluefile(self.vfs, 'kvfile').write(d)
+
+    def testcorruptedfile(self):
+        self.vfs.contents['badfile'] = 'ababagalamaga\n'
+        with self.assertRaisesRegexp(error.CorruptedState,
+                                     "dictionary.*element.*"):
+            scmutil.simplekeyvaluefile(self.vfs, 'badfile').read()
+
+if __name__ == "__main__":
+    silenttestrunner.main(__name__)