Improve the full diff by having more consistent indentation in the PrettyPrinter (#11571)

The normal default pretty printer is not great when objects are nested
and it can get hard to read the diff.

Instead, provide a pretty printer that behaves more like when json get
indented, which allows for smaller, more meaningful differences, at
the expense of a slightly longer diff.

This does not touch the other places where the pretty printer is used,
and only updated the full diff one.

Author: BenjaminSchubert

changelog/1531.improvement.rst

@@ -0,0 +1,4 @@
+Improved the very verbose diff for every standard library container types: the indentation is now consistent and the markers are on their own separate lines, which should reduce the diffs shown to users.
+
+Previously, the default python pretty printer was used to generate the output, which puts opening and closing
+markers on the same line as the first/last entry, in addition to not having consistent indentation.

src/_pytest/_io/pprint.py

@@ -58,7 +58,7 @@ def _safe_tuple(t):
 class PrettyPrinter:
     def __init__(
         self,
-        indent=1,
+        indent=4,
         width=80,
         depth=None,
         stream=None,
@@ -146,7 +146,6 @@ def _format(self, object, stream, indent, allowance, context, level):
 
     def _pprint_dataclass(self, object, stream, indent, allowance, context, level):
         cls_name = object.__class__.__name__
-        indent += len(cls_name) + 1
         items = [
             (f.name, getattr(object, f.name))
             for f in _dataclasses.fields(object)
@@ -164,17 +163,11 @@ def _pprint_dataclass(self, object, stream, indent, allowance, context, level):
     def _pprint_dict(self, object, stream, indent, allowance, context, level):
         write = stream.write
         write("{")
-        if self._indent_per_level > 1:
-            write((self._indent_per_level - 1) * " ")
-        length = len(object)
-        if length:
-            if self._sort_dicts:
-                items = sorted(object.items(), key=_safe_tuple)
-            else:
-                items = object.items()
-            self._format_dict_items(
-                items, stream, indent, allowance + 1, context, level
-            )
+        if self._sort_dicts:
+            items = sorted(object.items(), key=_safe_tuple)
+        else:
+            items = object.items()
+        self._format_dict_items(items, stream, indent, allowance, context, level)
         write("}")
 
     _dispatch[dict.__repr__] = _pprint_dict
@@ -185,32 +178,22 @@ def _pprint_ordered_dict(self, object, stream, indent, allowance, context, level
             return
         cls = object.__class__
         stream.write(cls.__name__ + "(")
-        self._format(
-            list(object.items()),
-            stream,
-            indent + len(cls.__name__) + 1,
-            allowance + 1,
-            context,
-            level,
-        )
+        self._pprint_dict(object, stream, indent, allowance, context, level)
         stream.write(")")
 
     _dispatch[_collections.OrderedDict.__repr__] = _pprint_ordered_dict
 
     def _pprint_list(self, object, stream, indent, allowance, context, level):
         stream.write("[")
-        self._format_items(object, stream, indent, allowance + 1, context, level)
+        self._format_items(object, stream, indent, allowance, context, level)
         stream.write("]")
 
     _dispatch[list.__repr__] = _pprint_list
 
     def _pprint_tuple(self, object, stream, indent, allowance, context, level):
         stream.write("(")
-        endchar = ",)" if len(object) == 1 else ")"
-        self._format_items(
-            object, stream, indent, allowance + len(endchar), context, level
-        )
-        stream.write(endchar)
+        self._format_items(object, stream, indent, allowance, context, level)
+        stream.write(")")
 
     _dispatch[tuple.__repr__] = _pprint_tuple
 
@@ -225,11 +208,8 @@ def _pprint_set(self, object, stream, indent, allowance, context, level):
         else:
             stream.write(typ.__name__ + "({")
             endchar = "})"
-            indent += len(typ.__name__) + 1
         object = sorted(object, key=_safe_key)
-        self._format_items(
-            object, stream, indent, allowance + len(endchar), context, level
-        )
+        self._format_items(object, stream, indent, allowance, context, level)
         stream.write(endchar)
 
     _dispatch[set.__repr__] = _pprint_set
@@ -319,7 +299,7 @@ def _pprint_bytearray(self, object, stream, indent, allowance, context, level):
 
     def _pprint_mappingproxy(self, object, stream, indent, allowance, context, level):
         stream.write("mappingproxy(")
-        self._format(object.copy(), stream, indent + 13, allowance + 1, context, level)
+        self._format(object.copy(), stream, indent, allowance, context, level)
         stream.write(")")
 
     _dispatch[_types.MappingProxyType.__repr__] = _pprint_mappingproxy
@@ -333,7 +313,6 @@ def _pprint_simplenamespace(
             cls_name = "namespace"
         else:
             cls_name = object.__class__.__name__
-        indent += len(cls_name) + 1
         items = object.__dict__.items()
         stream.write(cls_name + "(")
         self._format_namespace_items(items, stream, indent, allowance, context, level)
@@ -342,32 +321,30 @@ def _pprint_simplenamespace(
     _dispatch[_types.SimpleNamespace.__repr__] = _pprint_simplenamespace
 
     def _format_dict_items(self, items, stream, indent, allowance, context, level):
+        if not items:
+            return
+
         write = stream.write
-        indent += self._indent_per_level
-        delimnl = ",\n" + " " * indent
-        last_index = len(items) - 1
-        for i, (key, ent) in enumerate(items):
-            last = i == last_index
-            rep = self._repr(key, context, level)
-            write(rep)
+        item_indent = indent + self._indent_per_level
+        delimnl = "\n" + " " * item_indent
+        for key, ent in items:
+            write(delimnl)
+            write(self._repr(key, context, level))
             write(": ")
-            self._format(
-                ent,
-                stream,
-                indent + len(rep) + 2,
-                allowance if last else 1,
-                context,
-                level,
-            )
-            if not last:
-                write(delimnl)
+            self._format(ent, stream, item_indent, 1, context, level)
+            write(",")
+
+        write("\n" + " " * indent)
 
     def _format_namespace_items(self, items, stream, indent, allowance, context, level):
+        if not items:
+            return
+
         write = stream.write
-        delimnl = ",\n" + " " * indent
-        last_index = len(items) - 1
-        for i, (key, ent) in enumerate(items):
-            last = i == last_index
+        item_indent = indent + self._indent_per_level
+        delimnl = "\n" + " " * item_indent
+        for key, ent in items:
+            write(delimnl)
             write(key)
             write("=")
             if id(ent) in context:
@@ -378,52 +355,30 @@ def _format_namespace_items(self, items, stream, indent, allowance, context, lev
                 self._format(
                     ent,
                     stream,
-                    indent + len(key) + 1,
-                    allowance if last else 1,
+                    item_indent + len(key) + 1,
+                    1,
                     context,
                     level,
                 )
-            if not last:
-                write(delimnl)
+
+            write(",")
+
+        write("\n" + " " * indent)
 
     def _format_items(self, items, stream, indent, allowance, context, level):
-        write = stream.write
-        indent += self._indent_per_level
-        if self._indent_per_level > 1:
-            write((self._indent_per_level - 1) * " ")
-        delimnl = ",\n" + " " * indent
-        delim = ""
-        width = max_width = self._width - indent + 1
-        it = iter(items)
-        try:
-            next_ent = next(it)
-        except StopIteration:
+        if not items:
             return
-        last = False
-        while not last:
-            ent = next_ent
-            try:
-                next_ent = next(it)
-            except StopIteration:
-                last = True
-                max_width -= allowance
-                width -= allowance
-            if self._compact:
-                rep = self._repr(ent, context, level)
-                w = len(rep) + 2
-                if width < w:
-                    width = max_width
-                    if delim:
-                        delim = delimnl
-                if width >= w:
-                    width -= w
-                    write(delim)
-                    delim = ", "
-                    write(rep)
-                    continue
-            write(delim)
-            delim = delimnl
-            self._format(ent, stream, indent, allowance if last else 1, context, level)
+
+        write = stream.write
+        item_indent = indent + self._indent_per_level
+        delimnl = "\n" + " " * item_indent
+
+        for item in items:
+            write(delimnl)
+            self._format(item, stream, item_indent, 1, context, level)
+            write(",")
+
+        write("\n" + " " * indent)
 
     def _repr(self, object, context, level):
         repr, readable, recursive = self.format(
@@ -443,66 +398,45 @@ def format(self, object, context, maxlevels, level):
         return self._safe_repr(object, context, maxlevels, level)
 
     def _pprint_default_dict(self, object, stream, indent, allowance, context, level):
-        if not len(object):
-            stream.write(repr(object))
-            return
         rdf = self._repr(object.default_factory, context, level)
-        cls = object.__class__
-        indent += len(cls.__name__) + 1
-        stream.write(f"{cls.__name__}({rdf},\n{' ' * indent}")
-        self._pprint_dict(object, stream, indent, allowance + 1, context, level)
+        stream.write(f"{object.__class__.__name__}({rdf}, ")
+        self._pprint_dict(object, stream, indent, allowance, context, level)
         stream.write(")")
 
     _dispatch[_collections.defaultdict.__repr__] = _pprint_default_dict
 
     def _pprint_counter(self, object, stream, indent, allowance, context, level):
-        if not len(object):
-            stream.write(repr(object))
-            return
-        cls = object.__class__
-        stream.write(cls.__name__ + "({")
-        if self._indent_per_level > 1:
-            stream.write((self._indent_per_level - 1) * " ")
-        items = object.most_common()
-        self._format_dict_items(
-            items, stream, indent + len(cls.__name__) + 1, allowance + 2, context, level
-        )
-        stream.write("})")
+        stream.write(object.__class__.__name__ + "(")
+
+        if object:
+            stream.write("{")
+            items = object.most_common()
+            self._format_dict_items(items, stream, indent, allowance, context, level)
+            stream.write("}")
+
+        stream.write(")")
 
     _dispatch[_collections.Counter.__repr__] = _pprint_counter
 
     def _pprint_chain_map(self, object, stream, indent, allowance, context, level):
-        if not len(object.maps):
+        if not len(object.maps) or (len(object.maps) == 1 and not len(object.maps[0])):
             stream.write(repr(object))
             return
-        cls = object.__class__
-        stream.write(cls.__name__ + "(")
-        indent += len(cls.__name__) + 1
-        for i, m in enumerate(object.maps):
-            if i == len(object.maps) - 1:
-                self._format(m, stream, indent, allowance + 1, context, level)
-                stream.write(")")
-            else:
-                self._format(m, stream, indent, 1, context, level)
-                stream.write(",\n" + " " * indent)
+
+        stream.write(object.__class__.__name__ + "(")
+        self._format_items(object.maps, stream, indent, allowance, context, level)
+        stream.write(")")
 
     _dispatch[_collections.ChainMap.__repr__] = _pprint_chain_map
 
     def _pprint_deque(self, object, stream, indent, allowance, context, level):
-        if not len(object):
-            stream.write(repr(object))
-            return
-        cls = object.__class__
-        stream.write(cls.__name__ + "(")
-        indent += len(cls.__name__) + 1
+        stream.write(object.__class__.__name__ + "(")
+        if object.maxlen is not None:
+            stream.write("maxlen=%d, " % object.maxlen)
         stream.write("[")
-        if object.maxlen is None:
-            self._format_items(object, stream, indent, allowance + 2, context, level)
-            stream.write("])")
-        else:
-            self._format_items(object, stream, indent, 2, context, level)
-            rml = self._repr(object.maxlen, context, level)
-            stream.write(f"],\n{' ' * indent}maxlen={rml})")
+
+        self._format_items(object, stream, indent, allowance + 1, context, level)
+        stream.write("])")
 
     _dispatch[_collections.deque.__repr__] = _pprint_deque
 

src/_pytest/assertion/util.py

@@ -318,18 +318,6 @@ def _diff_text(left: str, right: str, verbose: int = 0) -> List[str]:
     return explanation
 
 
-def _surrounding_parens_on_own_lines(lines: List[str]) -> None:
-    """Move opening/closing parenthesis/bracket to own lines."""
-    opening = lines[0][:1]
-    if opening in ["(", "[", "{"]:
-        lines[0] = " " + lines[0][1:]
-        lines[:] = [opening] + lines
-    closing = lines[-1][-1:]
-    if closing in [")", "]", "}"]:
-        lines[-1] = lines[-1][:-1] + ","
-        lines[:] = lines + [closing]
-
-
 def _compare_eq_iterable(
     left: Iterable[Any],
     right: Iterable[Any],
@@ -341,20 +329,8 @@ def _compare_eq_iterable(
     # dynamic import to speedup pytest
     import difflib
 
-    left_formatting = pprint.pformat(left).splitlines()
-    right_formatting = pprint.pformat(right).splitlines()
-
-    # Re-format for different output lengths.
-    lines_left = len(left_formatting)
-    lines_right = len(right_formatting)
-    if lines_left != lines_right:
-        printer = PrettyPrinter()
-        left_formatting = printer.pformat(left).splitlines()
-        right_formatting = printer.pformat(right).splitlines()
-
-    if lines_left > 1 or lines_right > 1:
-        _surrounding_parens_on_own_lines(left_formatting)
-        _surrounding_parens_on_own_lines(right_formatting)
+    left_formatting = PrettyPrinter().pformat(left).splitlines()
+    right_formatting = PrettyPrinter().pformat(right).splitlines()
 
     explanation = ["Full diff:"]
     # "right" is the expected base against which we compare "left",