Fix lg to mathml conversion

Remove redundant parent <mrow> tags
Update confHist argument description

bin/confHist

@@ -46,8 +46,8 @@ then
 	echo "It is assumed that every .lg file in output_dir exists in target_dir, and a file"
 	echo "output_dir_vs_target_dir is created as output."
 	echo ""
-	echo "Output is written to the file confHist_outputs/CH_<output_dir_vs_target_dir>.html"
-	echo "or confHist_outputs/CH_<fileList>.html, depending upon the arguments used."
+	echo "Output is written to the file confHist_outputs/CH_<output_dir_vs_target_dir__size_<graphSize>_min_<minCount>.html"
+	echo "or confHist_outputs/CH_<fileList__size_<graphSize>_min_<minCount>.html, depending upon the arguments used."
 	exit 0
 fi
 

src/lg2txt.py

@@ -13,6 +13,7 @@
 
 import sys
 import csv
+from bs4 import BeautifulSoup
 from lg import *
 
 def readMapFile(fileName):
@@ -271,30 +272,45 @@ def translate(lg, segId,  segPrimMap, edgeMap,  symbolMap, structureMap):
 
     return nodeString
 
-def postprocess(mml_out):
-    # Add linebreaks for tags expect for mi, mo, mn
-    mml_out = mml_out.replace("><", ">\n<")
-    mml_out = mml_out.replace("</", "\n</")
-    mml_out = mml_out.replace("\n</mi", "</mi")
-    mml_out = mml_out.replace("\n</mo", "</mo")
-    mml_out = mml_out.replace("\n</mn", "</mn")
-    # tags with no indentation
-    constant_tags = ["mi", "mo", "mn"]
-    # Counts number of tab sapces
-    tab = 0
-    out = []
-    for line in mml_out.split("\n"):
-        if not line:
-            continue
-#     if re.match(r"<\w", line):
-        if line.startswith("<m"):
-            out.append(tab * "\t" + line)
-            if not line[1:3] in constant_tags:
-                tab += 1
-        elif line.startswith("</"):
-            tab -= 1
-            out.append(tab * "\t" + line)
-    return "\n".join(out)
+def cleanRows( mmlFile ):
+    # with open( filePath ) as mmlFile:
+    rowSoup = BeautifulSoup(mmlFile, 'html.parser')
+
+    mrows = rowSoup.find_all('mrow')
+
+    for item in mrows:
+        if item.parent.name == "mrow":
+                # REMOVING to avoid unexpected cases.
+                #or len( item.contents ) < 2:
+            item.unwrap()
+
+    return rowSoup.prettify()
+
+
+# def postprocess(mml_out):
+#     # Add linebreaks for tags expect for mi, mo, mn
+#     mml_out = mml_out.replace("><", ">\n<")
+#     mml_out = mml_out.replace("</", "\n</")
+#     mml_out = mml_out.replace("\n</mi", "</mi")
+#     mml_out = mml_out.replace("\n</mo", "</mo")
+#     mml_out = mml_out.replace("\n</mn", "</mn")
+#     # tags with no indentation
+#     constant_tags = ["mi", "mo", "mn"]
+#     # Counts number of tab sapces
+#     tab = 0
+#     out = []
+#     for line in mml_out.split("\n"):
+#         if not line:
+#             continue
+# #     if re.match(r"<\w", line):
+#         if line.startswith("<m"):
+#             out.append(tab * "\t" + line)
+#             if not line[1:3] in constant_tags:
+#                 tab += 1
+#         elif line.startswith("</"):
+#             tab -= 1
+#             out.append(tab * "\t" + line)
+#     return "\n".join(out)
 
 def main(lg_file, mapFile):
 
@@ -340,7 +356,8 @@ def main(lg_file, mapFile):
         # 		symbolMap, structureMap))
         mml_out_raw.append(translate(lg, root, segmentPrimitiveMap, 
                                 treeEdgeMap, symbolMap, structureMap))
-    mml_out = postprocess("\n".join(mml_out_raw)) 
+    # mml_out = postprocess("\n".join(mml_out_raw)) 
+    mml_out = cleanRows("\n".join(mml_out_raw)) 
     return mml_out
 
 if __name__ == '__main__':