summaryrefslogtreecommitdiffstats
path: root/src/lib/Bcfg2/Server/Lint/MergeFiles.py
diff options
context:
space:
mode:
authorSol Jerome <sol.jerome@gmail.com>2012-03-24 11:20:07 -0500
committerSol Jerome <sol.jerome@gmail.com>2012-03-24 11:20:07 -0500
commitdab1d03d81c538966d03fb9318a4588a9e803b44 (patch)
treef51e27fa55887e9fb961766805fe43f0da56c5b9 /src/lib/Bcfg2/Server/Lint/MergeFiles.py
parent5cd6238df496a3cea178e4596ecd87967cce1ce6 (diff)
downloadbcfg2-dab1d03d81c538966d03fb9318a4588a9e803b44.tar.gz
bcfg2-dab1d03d81c538966d03fb9318a4588a9e803b44.tar.bz2
bcfg2-dab1d03d81c538966d03fb9318a4588a9e803b44.zip
Allow to run directly from a git checkout (#1037)
Signed-off-by: Sol Jerome <sol.jerome@gmail.com>
Diffstat (limited to 'src/lib/Bcfg2/Server/Lint/MergeFiles.py')
-rw-r--r--src/lib/Bcfg2/Server/Lint/MergeFiles.py69
1 files changed, 69 insertions, 0 deletions
diff --git a/src/lib/Bcfg2/Server/Lint/MergeFiles.py b/src/lib/Bcfg2/Server/Lint/MergeFiles.py
new file mode 100644
index 000000000..56bca7931
--- /dev/null
+++ b/src/lib/Bcfg2/Server/Lint/MergeFiles.py
@@ -0,0 +1,69 @@
+import os
+import copy
+from difflib import SequenceMatcher
+import Bcfg2.Server.Lint
+
+class MergeFiles(Bcfg2.Server.Lint.ServerPlugin):
+ """ find Probes or Cfg files with multiple similar files that
+ might be merged into one """
+
+ def Run(self):
+ if 'Cfg' in self.core.plugins:
+ self.check_cfg()
+ if 'Probes' in self.core.plugins:
+ self.check_probes()
+
+ def check_cfg(self):
+ for filename, entryset in self.core.plugins['Cfg'].entries.items():
+ for mset in self.get_similar(entryset.entries):
+ self.LintError("merge-cfg",
+ "The following files are similar: %s. "
+ "Consider merging them into a single Genshi "
+ "template." %
+ ", ".join([os.path.join(filename, p)
+ for p in mset]))
+
+ def check_probes(self):
+ probes = self.core.plugins['Probes'].probes.entries
+ for mset in self.get_similar(probes):
+ self.LintError("merge-cfg",
+ "The following probes are similar: %s. "
+ "Consider merging them into a single probe." %
+ ", ".join([p for p in mset]))
+
+ def get_similar(self, entries):
+ if "threshold" in self.config:
+ # accept threshold either as a percent (e.g., "threshold=75") or
+ # as a ratio (e.g., "threshold=.75")
+ threshold = float(self.config['threshold'])
+ if threshold > 1:
+ threshold /= 100
+ else:
+ threshold = 0.75
+ rv = []
+ elist = entries.items()
+ while elist:
+ result = self._find_similar(elist.pop(0), copy.copy(elist),
+ threshold)
+ if len(result) > 1:
+ elist = [(fname, fdata)
+ for fname, fdata in elist
+ if fname not in result]
+ rv.append(result)
+ return rv
+
+ def _find_similar(self, ftuple, others, threshold):
+ fname, fdata = ftuple
+ rv = [fname]
+ while others:
+ cname, cdata = others.pop(0)
+ sm = SequenceMatcher(None, fdata.data, cdata.data)
+ # perform progressively more expensive comparisons
+ if (sm.real_quick_ratio() > threshold and
+ sm.quick_ratio() > threshold and
+ sm.ratio() > threshold):
+ rv.extend(self._find_similar((cname, cdata), copy.copy(others),
+ threshold))
+ return rv
+
+