Fix duplicate handling

Author: aradi

src/hsd/common.py

@@ -9,14 +9,10 @@
 """
 
 
-class HsdException(Exception):
+class HsdError(Exception):
     """Base class for exceptions in the HSD package."""
 
 
-class HsdParserError(HsdException):
-    """Base class for parser related errors."""
-
-
 def unquote(txt):
     """Giving string without quotes if enclosed in those."""
     if len(txt) >= 2 and (txt[0] in "\"'") and txt[-1] == txt[0]:

src/hsd/dictbuilder.py

@@ -8,7 +8,7 @@
 Contains an event-driven builder for dictionary based (JSON-like) structure
 """
 import re
-from .common import ATTRIB_SUFFIX, HSD_ATTRIB_SUFFIX
+from .common import ATTRIB_SUFFIX, HSD_ATTRIB_SUFFIX, HsdError
 from .eventhandler import HsdEventHandler
 
 
@@ -40,9 +40,9 @@ def __init__(self, flatten_data: bool = False,
                  include_hsd_attribs: bool = False):
         super().__init__()
         self._hsddict = {}
-        self._curblock = self._hsddict
+        self._content = self._hsddict  # Content obtained for the current node
         self._parentblocks = []
-        self._data = None
+        self._attribs = []
         self._flatten_data = flatten_data
         self._include_hsd_attribs = include_hsd_attribs
 
@@ -54,34 +54,51 @@ def hsddict(self):
 
 
     def open_tag(self, tagname, attrib, hsdattrib):
-        if attrib is not None:
-            self._curblock[tagname + ATTRIB_SUFFIX] = attrib
-        if self._include_hsd_attribs and hsdattrib is not None:
-            self._curblock[tagname + HSD_ATTRIB_SUFFIX] = hsdattrib
-        self._parentblocks.append(self._curblock)
-        self._curblock = {}
+        self._attribs.append((attrib, hsdattrib))
+        content = {} if self._content is None else self._content
+        self._parentblocks.append(content)
+        self._content = None
 
 
     def close_tag(self, tagname):
+        attrib, hsdattrib = self._attribs.pop(-1)
         parentblock = self._parentblocks.pop(-1)
-        prevcontent = parentblock.get(tagname)
-        if prevcontent is not None and not isinstance(prevcontent, list):
-            prevcontent = [prevcontent]
-            parentblock[tagname] = prevcontent
-        if self._data is None:
-            content = self._curblock
-        else:
-            content = self._data
-            self._data = None
-        if prevcontent is None:
+        prevcont = parentblock.get(tagname)
+        if prevcont is not None:
+            if isinstance(prevcont, dict) and isinstance(self._content, dict):
+                prevcont = [prevcont]
+                parentblock[tagname] = prevcont
+            elif not (isinstance(prevcont, list)
+                      and isinstance(prevcont[0], dict)):
+                msg = f"Invalid duplicate occurance of node '{tagname}'"
+                raise HsdError(msg)
+        content = {} if self._content is None else self._content
+        if prevcont is None:
             parentblock[tagname] = content
+            if attrib:
+                parentblock[tagname + ATTRIB_SUFFIX] = attrib
+            if self._include_hsd_attribs:
+                parentblock[tagname + HSD_ATTRIB_SUFFIX] = hsdattrib
         else:
-            prevcontent.append(content)
-        self._curblock = parentblock
+            prevcont.append(content)
+            prevattrib = parentblock.get(tagname + ATTRIB_SUFFIX)
+            if not (prevattrib is None and attrib is None):
+                msg = f"Duplicate node '{tagname}' should not carry attributes"
+            if self._include_hsd_attribs:
+                prevhsdattrib = parentblock.get(tagname + HSD_ATTRIB_SUFFIX)
+                if isinstance(prevhsdattrib, list):
+                    prevhsdattrib.append(hsdattrib)
+                else:
+                    parentblock[tagname + HSD_ATTRIB_SUFFIX] = [prevhsdattrib,
+                                                                hsdattrib]
+        self._content = parentblock
 
 
     def add_text(self, text):
-        self._data = self._text_to_data(text)
+        if self._content is not None:
+            msg = f"Data appeared in an invalid context"
+            raise HsdError(msg)
+        self._content = self._text_to_data(text)
 
 
     def _text_to_data(self, txt):

src/hsd/io.py

@@ -223,10 +223,11 @@ def _dump_dict(obj, fobj, indentstr, use_hsd_attribs):
         else:
             attribstr = " [" + attrib + "]"
         if use_hsd_attribs:
-            hsdattribs = obj.get(key + HSD_ATTRIB_SUFFIX)
-            if hsdattribs is not None:
-                key = hsdattribs.get("tag", key)
+            hsdattrib = obj.get(key + HSD_ATTRIB_SUFFIX)
+        else:
+            hsdattrib = None
         if isinstance(value, dict):
+            key = hsdattrib.get("tag", key) if hsdattrib else key
             if value:
                 fobj.write("{}{}{} {{\n".format(indentstr, key, attribstr))
                 _dump_dict(
@@ -235,12 +236,14 @@ def _dump_dict(obj, fobj, indentstr, use_hsd_attribs):
             else:
                 fobj.write("{}{}{} {{}}\n".format(indentstr, key, attribstr))
         elif isinstance(value, list) and value and isinstance(value[0], dict):
-            for item in value:
+            for ind, item in enumerate(value):
+                key = hsdattrib[ind].get("tag", key) if hsdattrib else key
                 fobj.write("{}{}{} {{\n".format(indentstr, key, attribstr))
                 _dump_dict(
                     item, fobj, indentstr + _INDENT_STR, use_hsd_attribs)
                 fobj.write("{}}}\n".format(indentstr))
         else:
+            key = hsdattrib.get("tag", key) if hsdattrib else key
             valstr = _get_hsd_rhs(value, indentstr)
             fobj.write("{}{}{} {}\n"\
                      .format(indentstr, key, attribstr, valstr))

src/hsd/parser.py

@@ -296,7 +296,7 @@ def _error(self, errorcode, lines):
         error_msg = (
             "Parsing error ({}) between lines {} - {} in file '{}'.".format(
                 errorcode, lines[0] + 1, lines[1] + 1, self._fname))
-        raise common.HsdParserError(error_msg)
+        raise common.HsdError(error_msg)
 
 
 

test/test.hsd

@@ -55,7 +55,7 @@ Analysis {
       Atoms = 1 2 3
       Label = "region1"
     }
-    Region {
+    REgion {
       Atoms = 1 2 3
       Label = "region2"
     }

test/test_dictbuilder.py

@@ -21,15 +21,15 @@ def test_dictbuilder():
 
 
 def test_dictbuilder_flat():
-    dictbuilder = hsd.HsdDictBuilder(flatten_data=True)
-    parser = hsd.HsdParser(eventhandler=dictbuilder)
+    dictbuilder = hsd.HsdDictBuilder(flatten_data=True, include_hsd_attribs=True)
+    parser = hsd.HsdParser(eventhandler=dictbuilder, lower_tag_names=True)
     with open(op.join(op.dirname(__file__), "test.hsd"), "r") as fobj:
         parser.feed(fobj)
     pyrep = dictbuilder.hsddict
     print("** Python structure with data flattening:\n")
     print(pyrep)
     print("\n** Turning back to HSD:\n")
-    print(hsd.dump_string(pyrep))
+    print(hsd.dump_string(pyrep, use_hsd_attribs=True))
 
 
 if __name__ == '__main__':