Longturtle improvements (#2500)

nicholascar · aucampia · pre-commit-ci[bot] · web-flow · commit 5ee8bd796049 · 2023-07-25T22:55:41.000+02:00
* small updates to the longturtle serializer and an improved test for it
* add docco

---------

Co-authored-by: Iwan Aucamp &lt;aucampia@gmail.com&gt;
Co-authored-by: pre-commit-ci[bot] &lt;66853113+pre-commit-ci[bot]@users.noreply.github.com&gt;
diff --git a/docs/plugin_serializers.rst b/docs/plugin_serializers.rst
@@ -32,7 +32,7 @@ xml        :class:`~rdflib.plugins.serializers.rdfxml.XMLSerializer`
 
 JSON-LD
 -------
-JSON-LD - 'json-ld' - has been incorprated in rdflib since v6.0.0.
+JSON-LD - 'json-ld' - has been incorporated into RDFLib since v6.0.0.
 
 HexTuples
 ---------
@@ -43,3 +43,12 @@ Hextuple) will be an empty string.
 
 For context-aware (multi-graph) serialization, the 'graph' field of the default graph will be an empty string and 
 the values for other graphs will be Blank Node IDs or IRIs.
+
+Longturtle
+----------
+Longturtle is just the turtle format with newlines preferred over compactness - multiple nodes on the same line 
+to enhance the format's text file version control (think Git) friendliness - and more modern forms of prefix markers - 
+PREFIX instead of @prefix - to make it as similar to SPARQL as possible.
+
+Longturtle is Turtle 1.1 compliant and will work wherever ordinary turtle works, however some very old parsers don't 
+understand PREFIX, only @prefix...
diff --git a/rdflib/plugins/serializers/longturtle.py b/rdflib/plugins/serializers/longturtle.py
@@ -13,7 +13,7 @@
     on the start of the next line
 * uses default encoding (encode()) is used instead of "latin-1"
 
-- Nicholas Car, 2021
+- Nicholas Car, 2023
 """
 
 from rdflib.exceptions import Error
@@ -101,7 +101,6 @@ def serialize(self, stream, base=None, encoding=None, spacious=None, **args):
                 self.write("\n")
 
         self.endDocument()
-        self.write("\n")
 
         self.base = None
 
@@ -168,21 +167,20 @@ def s_default(self, subject):
         self.path(subject, SUBJECT)
         self.write("\n" + self.indent())
         self.predicateList(subject)
-        self.write(" ;\n.")
+        self.write("\n.")
         return True
 
     def s_squared(self, subject):
         if (self._references[subject] > 0) or not isinstance(subject, BNode):
             return False
         self.write("\n" + self.indent() + "[]")
-        self.predicateList(subject)
+        self.predicateList(subject, newline=False)
         self.write(" ;\n.")
         return True
 
     def path(self, node, position, newline=False):
         if not (
-            self.p_squared(node, position, newline)
-            or self.p_default(node, position, newline)
+            self.p_squared(node, position) or self.p_default(node, position, newline)
         ):
             raise Error("Cannot serialize node '%s'" % (node,))
 
@@ -207,7 +205,11 @@ def label(self, node, position):
 
             return self.getQName(node, position == VERB) or node.n3()
 
-    def p_squared(self, node, position, newline=False):
+    def p_squared(
+        self,
+        node,
+        position,
+    ):
         if (
             not isinstance(node, BNode)
             or node in self._serialized
@@ -216,23 +218,19 @@ def p_squared(self, node, position, newline=False):
         ):
             return False
 
-        if not newline:
-            self.write(" ")
-
         if self.isValidList(node):
             # this is a list
             self.depth += 2
-            self.write("(\n")
-            self.depth -= 1
+            self.write(" (\n")
+            self.depth -= 2
             self.doList(node)
-            self.depth -= 1
-            self.write("\n" + self.indent(1) + ")")
+            self.write("\n" + self.indent() + ")")
         else:
+            # this is a Blank Node
             self.subjectDone(node)
-            self.depth += 2
-            self.write("[\n")
-            self.depth -= 1
-            self.predicateList(node, newline=False)
+            self.write("\n" + self.indent(1) + "[\n")
+            self.depth += 1
+            self.predicateList(node)
             self.depth -= 1
             self.write("\n" + self.indent(1) + "]")
 
@@ -279,6 +277,7 @@ def predicateList(self, subject, newline=False):
             self.write(" ;\n" + self.indent(1))
             self.verb(predicate, newline=True)
             self.objectList(properties[predicate])
+        self.write(" ;")
 
     def verb(self, node, newline=False):
         self.path(node, VERB, newline)
@@ -291,11 +290,13 @@ def objectList(self, objects):
         self.depth += depthmod
         first_nl = False
         if count > 1:
-            self.write("\n" + self.indent(1))
+            if not isinstance(objects[0], BNode):
+                self.write("\n" + self.indent(1))
             first_nl = True
         self.path(objects[0], OBJECT, newline=first_nl)
         for obj in objects[1:]:
-            self.write(" ,\n")
-            self.write(self.indent(1))
+            self.write(" ,")
+            if not isinstance(obj, BNode):
+                self.write("\n" + self.indent(1))
             self.path(obj, OBJECT, newline=True)
         self.depth -= depthmod
diff --git a/test/test_serializers/test_serializer_longturtle.py b/test/test_serializers/test_serializer_longturtle.py
