[python] Fork of the suffix-array extractor with surface improvements

Available as the cdec.sa module, with commande-line helpers:
python -m cdec.sa.compile -f ... -e ... -a ... -o sa-out/ -c extract.ini
python -m cdec.sa.extract -c extract.ini -g grammars-out/ < input.txt > input.sgml

+ renamed cdec.scfg -> cdec.sa
+ Python README

1 files changed, 29 insertions, 0 deletions

diff --git a/python/src/sa/_cdec_sa.pyx b/python/src/sa/_cdec_sa.pyx
new file mode 100644
index 00000000..710f8cb4
--- /dev/null
+++ b/python/src/sa/_cdec_sa.pyx
@@ -0,0 +1,29 @@
+import logging
+import resource
+import gzip
+
+cdef float monitor_cpu():
+    return (resource.getrusage(resource.RUSAGE_SELF).ru_utime+
+            resource.getrusage(resource.RUSAGE_SELF).ru_stime)
+
+def gzip_or_text(char* filename):
+    if filename.endswith('.gz'):
+        return gzip.GzipFile(filename)
+    else:
+        return open(filename)
+
+logger = logging.getLogger('cdec.sa')
+
+include "float_list.pxi"
+include "int_list.pxi"
+include "str_map.pxi"
+include "data_array.pxi"
+include "alignment.pxi"
+include "bilex.pxi"
+include "veb.pxi"
+include "lcp.pxi"
+include "sym.pxi"
+include "rule.pxi"
+include "precomputation.pxi"
+include "suffix_array.pxi"
+include "rulefactory.pxi"