Pull combine_parallel_data out of CoverageData

3 files changed, 77 insertions, 73 deletions

diff --git a/coverage/control.py b/coverage/control.py
index 1760ee78..2f084cc2 100644
--- a/coverage/control.py
+++ b/coverage/control.py
@@ -15,7 +15,7 @@ from coverage.annotate import AnnotateReporter
 from coverage.backward import string_class, iitems
 from coverage.collector import Collector
 from coverage.config import read_coverage_config
-from coverage.data import CoverageData
+from coverage.data import CoverageData, combine_parallel_data
 from coverage.debug import DebugControl, write_formatted_info
 from coverage.disposition import disposition_debug_msg
 from coverage.files import PathAliases, set_relative_directory, abs_file
@@ -536,7 +536,7 @@ class Coverage(object):
                 for pattern in paths[1:]:
                     aliases.add(pattern, result)
 
-        self._data.combine_parallel_data(aliases=aliases, data_paths=data_paths, strict=strict)
+        combine_parallel_data(self._data, aliases=aliases, data_paths=data_paths, strict=strict)
 
     def get_data(self):
         """Get the collected data.
diff --git a/coverage/data.py b/coverage/data.py
index e9243166..0b3b640b 100644
--- a/coverage/data.py
+++ b/coverage/data.py
@@ -594,69 +594,6 @@ class CoverageJsonData(object):
 
         self._validate()
 
-    def combine_parallel_data(self, aliases=None, data_paths=None, strict=False):
-        """Combine a number of data files together.
-
-        Treat `self.filename` as a file prefix, and combine the data from all
-        of the data files starting with that prefix plus a dot.
-
-        If `aliases` is provided, it's a `PathAliases` object that is used to
-        re-map paths to match the local machine's.
-
-        If `data_paths` is provided, it is a list of directories or files to
-        combine.  Directories are searched for files that start with
-        `self.filename` plus dot as a prefix, and those files are combined.
-
-        If `data_paths` is not provided, then the directory portion of
-        `self.filename` is used as the directory to search for data files.
-
-        Every data file found and combined is then deleted from disk. If a file
-        cannot be read, a warning will be issued, and the file will not be
-        deleted.
-
-        If `strict` is true, and no files are found to combine, an error is
-        raised.
-
-        """
-        # Because of the os.path.abspath in the constructor, data_dir will
-        # never be an empty string.
-        data_dir, local = os.path.split(self.filename)
-        localdot = local + '.*'
-
-        data_paths = data_paths or [data_dir]
-        files_to_combine = []
-        for p in data_paths:
-            if os.path.isfile(p):
-                files_to_combine.append(os.path.abspath(p))
-            elif os.path.isdir(p):
-                pattern = os.path.join(os.path.abspath(p), localdot)
-                files_to_combine.extend(glob.glob(pattern))
-            else:
-                raise CoverageException("Couldn't combine from non-existent path '%s'" % (p,))
-
-        if strict and not files_to_combine:
-            raise CoverageException("No data to combine")
-
-        files_combined = 0
-        for f in files_to_combine:
-            new_data = CoverageData(debug=self._debug)
-            try:
-                new_data._read_file(f)
-            except CoverageException as exc:
-                if self._warn:
-                    # The CoverageException has the file name in it, so just
-                    # use the message as the warning.
-                    self._warn(str(exc))
-            else:
-                self.update(new_data, aliases=aliases)
-                files_combined += 1
-                if self._debug and self._debug.should('dataio'):
-                    self._debug.write("Deleting combined data file %r" % (f,))
-                file_be_gone(f)
-
-        if strict and not files_combined:
-            raise CoverageException("No usable data files")
-
     ##
     ## Miscellaneous
     ##
@@ -731,9 +668,76 @@ class CoverageJsonData(object):
         return self._arcs is not None
 
 
-from coverage.sqldata import CoverageSqliteData
-CoverageData = CoverageSqliteData
+which = os.environ.get("COV_STORAGE", "json")
+if which == "json":
+    CoverageData = CoverageJsonData
+elif which == "sql":
+    from coverage.sqldata import CoverageSqliteData
+    CoverageData = CoverageSqliteData
+
 
+def combine_parallel_data(data, aliases=None, data_paths=None, strict=False):
+    """Combine a number of data files together.
+
+    Treat `data.filename` as a file prefix, and combine the data from all
+    of the data files starting with that prefix plus a dot.
+
+    If `aliases` is provided, it's a `PathAliases` object that is used to
+    re-map paths to match the local machine's.
+
+    If `data_paths` is provided, it is a list of directories or files to
+    combine.  Directories are searched for files that start with
+    `data.filename` plus dot as a prefix, and those files are combined.
+
+    If `data_paths` is not provided, then the directory portion of
+    `data.filename` is used as the directory to search for data files.
+
+    Every data file found and combined is then deleted from disk. If a file
+    cannot be read, a warning will be issued, and the file will not be
+    deleted.
+
+    If `strict` is true, and no files are found to combine, an error is
+    raised.
+
+    """
+    # Because of the os.path.abspath in the constructor, data_dir will
+    # never be an empty string.
+    data_dir, local = os.path.split(data.filename)
+    localdot = local + '.*'
+
+    data_paths = data_paths or [data_dir]
+    files_to_combine = []
+    for p in data_paths:
+        if os.path.isfile(p):
+            files_to_combine.append(os.path.abspath(p))
+        elif os.path.isdir(p):
+            pattern = os.path.join(os.path.abspath(p), localdot)
+            files_to_combine.extend(glob.glob(pattern))
+        else:
+            raise CoverageException("Couldn't combine from non-existent path '%s'" % (p,))
+
+    if strict and not files_to_combine:
+        raise CoverageException("No data to combine")
+
+    files_combined = 0
+    for f in files_to_combine:
+        try:
+            new_data = CoverageData(f, debug=data._debug)
+            new_data.read()
+        except CoverageException as exc:
+            if data._warn:
+                # The CoverageException has the file name in it, so just
+                # use the message as the warning.
+                data._warn(str(exc))
+        else:
+            data.update(new_data, aliases=aliases)
+            files_combined += 1
+            if data._debug and data._debug.should('dataio'):
+                data._debug.write("Deleting combined data file %r" % (f,))
+            file_be_gone(f)
+
+    if strict and not files_combined:
+        raise CoverageException("No usable data files")
 
 def canonicalize_json_data(data):
     """Canonicalize our JSON data so it can be compared."""
diff --git a/tests/test_data.py b/tests/test_data.py
index 5deccef0..702f4554 100644
--- a/tests/test_data.py
+++ b/tests/test_data.py
@@ -11,7 +11,7 @@ import re
 
 import mock
 
-from coverage.data import CoverageData, debug_main, canonicalize_json_data
+from coverage.data import CoverageData, debug_main, canonicalize_json_data, combine_parallel_data
 from coverage.debug import DebugControlString
 from coverage.files import PathAliases, canonical_filename
 from coverage.misc import CoverageException
@@ -611,7 +611,7 @@ class CoverageDataFilesTest(DataTestHelpers, CoverageTest):
         self.assert_exists(".coverage.2")
 
         covdata3 = CoverageData()
-        covdata3.combine_parallel_data()
+        combine_parallel_data(covdata3)
         self.assert_line_counts(covdata3, SUMMARY_1_2)
         self.assert_measured_files(covdata3, MEASURED_FILES_1_2)
         self.assert_doesnt_exist(".coverage.1")
@@ -713,7 +713,7 @@ class CoverageDataFilesTest(DataTestHelpers, CoverageTest):
         aliases = PathAliases()
         aliases.add("/home/ned/proj/src/", "./")
         aliases.add(r"c:\ned\test", "./")
-        covdata3.combine_parallel_data(aliases=aliases)
+        combine_parallel_data(covdata3, aliases=aliases)
 
         apy = canonical_filename('./a.py')
         sub_bpy = canonical_filename('./sub/b.py')
@@ -740,7 +740,7 @@ class CoverageDataFilesTest(DataTestHelpers, CoverageTest):
         covdata_xxx.write()
 
         covdata3 = CoverageData()
-        covdata3.combine_parallel_data(data_paths=['cov1', 'cov2'])
+        combine_parallel_data(covdata3, data_paths=['cov1', 'cov2'])
 
         self.assert_line_counts(covdata3, SUMMARY_1_2)
         self.assert_measured_files(covdata3, MEASURED_FILES_1_2)
@@ -769,7 +769,7 @@ class CoverageDataFilesTest(DataTestHelpers, CoverageTest):
         covdata_2xxx.write()
 
         covdata3 = CoverageData()
-        covdata3.combine_parallel_data(data_paths=['cov1', 'cov2/.coverage.2'])
+        combine_parallel_data(covdata3, data_paths=['cov1', 'cov2/.coverage.2'])
 
         self.assert_line_counts(covdata3, SUMMARY_1_2)
         self.assert_measured_files(covdata3, MEASURED_FILES_1_2)
@@ -782,4 +782,4 @@ class CoverageDataFilesTest(DataTestHelpers, CoverageTest):
         covdata = CoverageData()
         msg = "Couldn't combine from non-existent path 'xyzzy'"
         with self.assertRaisesRegex(CoverageException, msg):
-            covdata.combine_parallel_data(data_paths=['xyzzy'])
+            combine_parallel_data(covdata, data_paths=['xyzzy'])