Move xml_indent, xml_quote and xml_unquote to osc.util.xml module

osc/_private/api.py

@@ -7,6 +7,10 @@
 import xml.sax.saxutils
 from xml.etree import ElementTree as ET
 
+from ..util.xml import xml_escape
+from ..util.xml import xml_indent
+from ..util.xml import xml_unescape
+
 
 def get(apiurl, path, query=None):
     """
@@ -205,41 +209,3 @@
     if indent:
         xml_indent(node)
     ET.ElementTree(node).write(path)
-
-
-def xml_escape(string):
-    """
-    Escape the string so it's safe to use in XML and xpath.
-    """
-    entities = {
-        "\"": """,
-        "'": "'",
-    }
-    if isinstance(string, bytes):
-        return xml.sax.saxutils.escape(string.decode("utf-8"), entities=entities).encode("utf-8")
-    return xml.sax.saxutils.escape(string, entities=entities)
-
-
-def xml_unescape(string):
-    """
-    Decode XML entities in the string.
-    """
-    entities = {
-        """: "\"",
-        "'": "'",
-    }
-    if isinstance(string, bytes):
-        return xml.sax.saxutils.unescape(string.decode("utf-8"), entities=entities).encode("utf-8")
-    return xml.sax.saxutils.unescape(string, entities=entities)
-
-
-def xml_indent(root):
-    """
-    Indent XML so it looks pretty after printing or saving to file.
-    """
-    if hasattr(ET, "indent"):
-        # ElementTree supports indent() in Python 3.9 and newer
-        ET.indent(root)
-    else:
-        from .. import core as osc_core
-        osc_core.xmlindent(root)

osc/core.py

@@ -54,6 +54,7 @@
 from .connection import http_request, http_GET, http_POST, http_PUT, http_DELETE
 from .store import Store
 from .util.helper import decode_list, decode_it, raw_input, _html_escape
+from .util.xml import xml_indent_compat as xmlindent
 
 
 ET_ENCODING = "unicode"
@@ -636,26 +637,6 @@
     def haserror(self):
         return self.error is not None
 
-# http://effbot.org/zone/element-lib.htm#prettyprint
-
-
-def xmlindent(elem, level=0):
-    i = "\n" + level * "  "
-    if isinstance(elem, ET.ElementTree):
-        elem = elem.getroot()
-    if len(elem):
-        if not elem.text or not elem.text.strip():
-            elem.text = i + "  "
-        for e in elem:
-            xmlindent(e, level + 1)
-            if not e.tail or not e.tail.strip():
-                e.tail = i + "  "
-        if not e.tail or not e.tail.strip():
-            e.tail = i
-    else:
-        if level and (not elem.tail or not elem.tail.strip()):
-            elem.tail = i
-
 
 class Project:
     """
@@ -6137,27 +6118,27 @@
     # BEGIN: Error out on branching scmsync packages; this should be properly handled in the API
 
     # read src_package meta
     m = b"".join(show_package_meta(apiurl, src_project, src_package))
     root = ET.fromstring(m)
 
     devel_project = None
     devel_package = None
     if not nodevelproject:
         devel_node = root.find("devel")
         if devel_node is not None:
             devel_project = devel_node.get("project")
             devel_package = devel_node.get("package", src_package)
         if devel_project:
             # replace src_package meta with devel_package meta because we're about branch from devel
             m = b"".join(show_package_meta(apiurl, devel_project, devel_package))
             root = ET.fromstring(m)
 
     # error out if we're branching a scmsync package (we'd end up with garbage anyway)
     if root.find("scmsync") is not None:
         msg = "Cannot branch a package with <scmsync> set."
         if devel_project:
             raise oscerr.PackageError(devel_project, devel_package, msg)
         raise oscerr.PackageError(src_project, src_package, msg)
 
     # END: Error out on branching scmsync packages; this should be properly handled in the API
 

osc/util/xml.py

@@ -0,0 +1,81 @@
+"""
+Functions that manipulate with XML.
+"""
+
+
+import xml.sax.saxutils
+from xml.etree import ElementTree as ET
+
+
+def xml_escape(string):
+    """
+    Escape the string so it's safe to use in XML and xpath.
+    """
+    entities = {
+        '"': """,
+        "'": "'",
+    }
+    if isinstance(string, bytes):
+        return xml.sax.saxutils.escape(string.decode("utf-8"), entities=entities).encode("utf-8")
+    return xml.sax.saxutils.escape(string, entities=entities)
+
+
+def xml_unescape(string):
+    """
+    Decode XML entities in the string.
+    """
+    entities = {
+        """: '"',
+        "'": "'",
+    }
+    if isinstance(string, bytes):
+        return xml.sax.saxutils.unescape(string.decode("utf-8"), entities=entities).encode("utf-8")
+    return xml.sax.saxutils.unescape(string, entities=entities)
+
+
+def xml_strip_text(node):
+    """
+    Recursively strip inner text in nodes:
+    - if text contains only whitespaces
+    - if node contains child nodes
+    """
+    if node.text and not node.text.strip():
+        node.text = None
+    elif len(node) != 0:
+        node.text = None
+    for child in node:
+        xml_strip_text(child)
+
+
+def xml_indent_compat(elem, level=0):
+    """
+    XML indentation code for python < 3.9.
+    Source: http://effbot.org/zone/element-lib.htm#prettyprint
+    """
+    i = "\n" + level * "  "
+    if isinstance(elem, ET.ElementTree):
+        elem = elem.getroot()
+    if len(elem):
+        if not elem.text or not elem.text.strip():
+            elem.text = i + "  "
+        for e in elem:
+            xml_indent_compat(e, level + 1)
+            if not e.tail or not e.tail.strip():
+                e.tail = i + "  "
+        if not e.tail or not e.tail.strip():
+            e.tail = i
+    else:
+        if level and (not elem.tail or not elem.tail.strip()):
+            elem.tail = i
+
+
+def xml_indent(root):
+    """
+    Indent XML so it looks pretty after printing or saving to file.
+    """
+    if hasattr(ET, "indent"):
+        # ElementTree supports indent() in Python 3.9 and newer
+        xml_strip_text(root)
+        ET.indent(root)
+    else:
+        xml_indent_compat(root)