From be5a70d3aa1c30d7c86d77649b747de2838566ce Mon Sep 17 00:00:00 2001
From: sienkiew <sienkiew@d34015c8-bcbb-4646-8ac8-8ba5febf221d>
Date: Thu, 21 Jul 2011 15:17:58 +0000
Subject: initial import of yapps from debian sources

git-svn-id: http://svn.stsci.edu/svn/ssb/etal/exyapps/trunk@356 d34015c8-bcbb-4646-8ac8-8ba5febf221d
---
 examples/xml.g | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)
 create mode 100644 examples/xml.g

(limited to 'examples/xml.g')

diff --git a/examples/xml.g b/examples/xml.g
new file mode 100644
index 0000000..cec2709
--- /dev/null
+++ b/examples/xml.g
@@ -0,0 +1,66 @@
+#!/usr/bin/python2
+
+# xml.g
+#
+# Amit J. Patel, August 2003
+#
+# Simple (non-conforming, non-validating) parsing of XML documents,
+# based on Robert D. Cameron's "REX" shallow parser.  It doesn't
+# handle CDATA and lots of other stuff; it's meant to demonstrate
+# Yapps, not replace a proper XML parser.
+
+%%
+
+parser xml:
+    token nodetext: r'[^<>]+'
+    token attrtext_singlequote: "[^']*"
+    token attrtext_doublequote: '[^"]*'
+    token SP: r'\s'
+    token id: r'[a-zA-Z_:][a-zA-Z0-9_:.-]*'
+
+    rule node:
+        r'<!--.*?-->'                   {{ return ['!--comment'] }}
+      | r'<!\[CDATA\[.*?\]\]>'          {{ return ['![CDATA['] }}
+      | r'<!' SP* id '[^>]*>'           {{ return ['!doctype'] }}
+      | '<' SP* id SP* attributes SP*   {{ startid = id }}
+        ( '>' nodes '</' SP* id SP* '>' {{ assert startid == id, 'Mismatched tags <%s> ... </%s>' % (startid, id) }}
+                                        {{ return [id, attributes] + nodes }}
+        | '/\s*>'                       {{ return [id, attributes] }}
+        )
+      | nodetext                        {{ return nodetext }}
+
+    rule nodes:                         {{ result = [] }}
+         ( node                         {{ result.append(node) }}
+         ) *                            {{ return result }}
+
+    rule attribute: id SP* '=' SP*
+         ( '"' attrtext_doublequote '"' {{ return (id, attrtext_doublequote) }}
+         | "'" attrtext_singlequote "'" {{ return (id, attrtext_singlequote) }}
+         )
+
+    rule attributes:                    {{ result = {} }}
+         ( attribute SP*                {{ result[attribute[0]] = attribute[1] }}
+         ) *                            {{ return result }}
+
+%%
+
+if __name__ == '__main__':
+    tests = ['<!-- hello -->',
+             'some text',
+             '< bad xml',
+             '<br />',
+             '<     spacey      a  =   "foo"    /   >',
+             '<a href="foo">text ... </a>',
+             '<begin> middle </end>',
+             '<begin> <nested attr=\'baz\' another="hey"> foo </nested> <nested> bar </nested> </begin>',
+            ]
+    print
+    print '____Running tests_______________________________________'
+    for test in tests:
+        print
+        try:
+            parser = xml(xmlScanner(test))
+            output = '%s ==> %s' % (repr(test), repr(parser.node()))
+        except (yappsrt.SyntaxError, AssertionError), e:
+            output = '%s ==> FAILED ==> %s' % (repr(test), e)
+        print output
-- 
cgit