project-open-data · andreamedinasmith · Jun 30, 2015
diff --git a/Metadata_XSD/POD_v1_1.xsd b/Metadata_XSD/POD_v1_1.xsd
diff --git a/Metadata_XSD/POD_v1_1.xsl b/Metadata_XSD/POD_v1_1.xsl
@@ -0,0 +1,131 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+  xmlns:xs="http://www.w3.org/2001/XMLSchema"
+  exclude-result-prefixes="xs"
+  version="2.0">
+
+  <xsl:output encoding="UTF-8" method="text"/>
+  <xsl:strip-space elements="*"/>
+
+  <xsl:template match="/">
+    <xsl:apply-templates/>
+  </xsl:template>
+
+  <xsl:template match="catalog">
+    {
+    <xsl:apply-templates select="type | context | id" />
+    <xsl:apply-templates select="conformsTo | describedBy"/>
+    "dataset":[
+    <xsl:apply-templates select="dataset"/>
+    ]
+    }
+  </xsl:template>
+
+	<xsl:template match="context | id">
+		"@<xsl:value-of select="local-name()"/>":"<xsl:value-of select="."/>",
+	</xsl:template>
+
+	<xsl:template match="type">
+		"@<xsl:value-of select="local-name()"/>":"<xsl:value-of select="."/>" <xsl:if test="position() != last()">,</xsl:if>
+	</xsl:template>
+
+	<xsl:template match="dataset">
+    {
+    <xsl:apply-templates/>
+    }<xsl:if test="position() != last()">,</xsl:if>
+  </xsl:template>
+
+  <xsl:template match="contactPoint">
+    "<xsl:value-of select="local-name()"/>":{
+    <xsl:apply-templates/>
+    },
+  </xsl:template>
+
+  <xsl:template match="hasEmail">
+    "<xsl:value-of select="local-name()"/>":"mailto:<xsl:value-of select="."/>"
+  </xsl:template>
+
+  <xsl:template match="keyword">
+    "<xsl:value-of select="local-name()"/>":[
+    <xsl:apply-templates/>
+    ],
+  </xsl:template>
+
+  <xsl:template match="item">
+    "<xsl:value-of select="normalize-space(.)"/>" <xsl:if test="position() != last()">,</xsl:if>
+  </xsl:template>
+
+ <!-- <xsl:template match="keyword"/>-->
+
+  <xsl:template match="publisher">
+    "<xsl:value-of select="local-name()"/>":{
+    <xsl:apply-templates select="@* | *"/>
+    },
+  </xsl:template>
+
+  <xsl:template match="subOrganizationOf">
+    "<xsl:value-of select="local-name()"/>":{
+    <xsl:apply-templates select="@* | *"/>
+    }
+  </xsl:template>
+
+  <xsl:template match="bureauCode | programCode">
+    "<xsl:value-of select="local-name()"/>":[
+    "<xsl:value-of select="."/>"
+    ],
+  </xsl:template>
+
+  <xsl:template match="dataQuality">
+    "<xsl:value-of select="local-name()"/>":<xsl:value-of select="."/>,
+  </xsl:template>
+
+  <xsl:template match="distribution[1]">
+    "<xsl:value-of select="local-name()"/>":[
+    {
+    <xsl:apply-templates select="@* | *"/>
+    }<xsl:if test="position() != last()">,</xsl:if>
+    <xsl:apply-templates select="following-sibling::distribution" mode="pull"/>
+    ] <xsl:if test="following-sibling::*">,</xsl:if>
+  </xsl:template>
+
+  <xsl:template match="distribution" mode="pull">
+    {
+    <xsl:apply-templates select="@* | *"/>
+    }<xsl:if test="position() != last()">,</xsl:if>
+    <xsl:apply-templates select="following-sibling::distribution"/>
+  </xsl:template>
+
+  <xsl:template match="distribution"/>
+
+  <xsl:template match="language">
+  <xsl:if test="item[. != '']">  "<xsl:value-of select="local-name()"/>":[
+    <xsl:apply-templates/>
+    ]<xsl:if test="following-sibling::*">,</xsl:if></xsl:if>
+     </xsl:template>
+
+  <xsl:template match="references">
+    "<xsl:value-of select="local-name()"/>":[
+    <xsl:apply-templates/>
+    ]<xsl:if test="following-sibling::*">,</xsl:if>
+  </xsl:template>
+
+  <xsl:template match="url">
+    "<xsl:value-of select="."/>"<xsl:if test="position() != last()">,</xsl:if>
+  </xsl:template>
+
+  <xsl:template match="theme" >
+    <xsl:if test="item[. != '']">"<xsl:value-of select="local-name()"/>":[
+    <xsl:apply-templates/>
+    ]<xsl:if test="following-sibling::*">,</xsl:if></xsl:if>
+  </xsl:template>
+
+  <xsl:template match="@*">
+    "@<xsl:value-of select="local-name()"/>":"<xsl:value-of select="."/>",<xsl:text>&#x000a;</xsl:text>
+  </xsl:template>
+
+  <xsl:template match="*">
+   <xsl:if test=". != ''"> "<xsl:value-of select="local-name()"/>":"<xsl:value-of select="normalize-space(.)"/>"<xsl:if test="following-sibling::*[. != '']">,</xsl:if>
+    <xsl:apply-templates select="*"/></xsl:if>
+  </xsl:template>
+
+</xsl:stylesheet>
diff --git a/Metadata_XSD/README.md b/Metadata_XSD/README.md
@@ -0,0 +1,47 @@
+Notes:
+
+The following files can be found in this folder:
+1. POD_v1_1.xsd 
+    * This is an xml representation of the (federal) Project Open Data v1.1 json schema
+
+ 2. dataGovSample.xml
+     * This is the content from the sample file (for the 'extended' POD fields)
+        https://project-open-data.cio.gov/v1.1/examples/catalog-sample-extended.json
+        expressed in xml valid to POD_v1_1.xsd
+
+3. POD_v1_1.xsl
+     * This is an xsl stylesheet that converts xml valid to POD_v1_1.xsd to json.
+     * This stylesheet was developed using xml that reproduced the information found in
+        the file https://project-open-data.cio.gov/v1.1/examples/catalog-sample-extended.json.
+     * It is possible that there are xml files that could be valid to the POD_v1_1.xsd for 
+       which this stylesheet makes an incomplete or incorrect conversion.
+
+ 4. dataGovSample.json
+     * This is the json file created from dataGovSample.xml using POD_v1_1.xsl.   
+
+5. nistSample.xml
+     * This is a file containing two records that are present in NIST's data.gov json
+
+ 6. nistSample.json
+     * This is the json file created from nistSample.xml using POD_v1_1.xsl. 
+
+
+
+As of 26 June 2015:
+
+1. The files dataGovSample.xml and nistSample.xml are valid to POD_v1_1.xsd.  
+
+2. The files dataGovSample.json and nistSample.json were created from their
+    similarly named xml files using POD_v1_1.xsl. 
+
+3. The files dataGovSample.json and nistSample.json were validated against the 
+    Federal v1.1 schema using the Project Open Data Dashboard.
+
+Note about testing the xml to json conversion:
+      * The xsl stysheet is declared as version="2.0"  and has been mostly run 
+        using Saxon 9x in the Oxygen environment.   
+      * The stylesheet has been  successfully tested (although not extensively) using 
+         a declaration of version="1.0" and run under Saxon 6.5.5 in Oxygen.  No testing 
+        has been done with other parsers and/or transformation engines.
+
+
diff --git a/Metadata_XSD/README.txt b/Metadata_XSD/README.txt
@@ -0,0 +1,47 @@
+Notes:
+
+The following files can be found in this folder:
+1. POD_v1_1.xsd 
+    * This is an xml representation of the Federal v1.1 json schema
+
+ 2. dataGovSample.xml
+     * This is the content from the sample file (for the 'extended' POD fields)
+        https://project-open-data.cio.gov/v1.1/examples/catalog-sample-extended.json
+        expressed in xml valid to POD_v1_1.xsd
+
+3. POD_v1_1.xsl
+     * This is an xsl stylesheet that converts xml valid to POD_v1_1.xsd to json.
+     * This stylesheet was developed using xml that reproduced the information found in
+        the file https://project-open-data.cio.gov/v1.1/examples/catalog-sample-extended.json.
+     * It is possible that there are xml files that could be valid to the POD_v1_1.xsd for 
+       which this stylesheet makes an incomplete or incorrect conversion.
+
+ 4. dataGovSample.json
+     * This is the json file created from dataGovSample.xml using POD_v1_1.xsl.   
+
+5. nistSample.xml
+     * This is a file containing two records that are present in NIST's data.gov json
+
+ 6. nistSample.json
+     * This is the json file created from nistSample.xml using POD_v1_1.xsl. 
+
+
+
+As of 26 June 2015:
+
+1. The files dataGovSample.xml and nistSample.xml are valid to POD_v1_1.xsd.  
+
+2. The files dataGovSample.json and nistSample.json were created from their
+    similarly named xml files using POD_v1_1.xsl. 
+
+3. The files dataGovSample.json and nistSample.json were validated against the 
+    Federal v1.1 schema using the Project Open Data Dashboard.
+
+Note about testing the xml to json conversion:
+      * The xsl stysheet is declared as version="2.0"  and has been mostly run 
+        using Saxon 9x in the Oxygen environment.   
+      * The stylesheet has been  successfully tested (although not extensively) using 
+         a declaration of version="1.0" and run under Saxon 6.5.5 in Oxygen.  No testing 
+        has been done with other parsers and/or transformation engines.
+
+
diff --git a/Metadata_XSD/dataGovSample.json b/Metadata_XSD/dataGovSample.json
@@ -0,0 +1,97 @@
+{
+  "@type": "dcat:Catalog",
+  "@context": "https://project-open-data.cio.gov/v1.1/schema/catalog.jsonld",
+  "@id": "http://www.agency.gov/data.json",
+  "conformsTo": "https://project-open-data.cio.gov/v1.1/schema",
+  "describedBy": "https://project-open-data.cio.gov/v1.1/schema/catalog.json",
+  "dataset": [{
+    "title": "U.S. Widget Manufacturing Statistics",
+    "description": "This dataset provides national statistics on the production of widgets",
+    "contactPoint": {
+      "@type": "vcard:Contact",
+      "fn": "Jane Doe",
+      "hasEmail": "mailto:[email protected]"
+    },
+    "keyword": [
+      "widget",
+      "manufacturing",
+      "factory"
+    ],
+    "modified": "2011-11-19",
+    "publisher": {
+      "@type": "org:Organization",
+      "name": "Widget Services",
+      "subOrganizationOf": {
+        "@type": "org:Organization",
+        "name": "Office of Citizen Services and Innovative Technologies",
+        "subOrganizationOf": {
+          "@type": "org:Organization",
+          "name": "General Services Administration",
+          "subOrganizationOf": {
+            "@type": "org:Organization",
+            "name": "U.S. Government"
+          }
+        }
+      }
+    },
+    "accessLevel": "public",
+    "identifier": "http://dx.doi.org/10.7927/H4PZ56R2",
+    "bureauCode": ["018:10"],
+    "programCode": ["018:001"],
+    "accrualPeriodicty": "R/P1Y",
+    "conformsTo": "https://project-open-data.cio.gov/v1.1/schema",
+    "describedBy": "https://project-open-data.cio.gov/v1.1/schema/catalog.json",
+    "dataQuality": true,
+    "distribution": [
+      {
+        "description": "Widgets data as a CSV file",
+        "downloadURL": "https://data.agency.gov/datasets/widgets-statistics/widgets.csv",
+        "format": "CSV",
+        "mediaType": "text/csv",
+        "title": "widgets.csv",
+        "@type": "dcat:Distribution"
+      },
+      {
+        "description": "Widgets data as a zipped CSV file with attached data dictionary",
+        "downloadURL": "https://data.agency.gov/datasets/widgets-statistics/widgets-all.zip",
+        "format": "Zipped CSV",
+        "mediaType": "application/zip",
+        "title": "widgets-all.zip",
+        "@type": "dcat:Distribution"
+      },
+      {
+        "conformsTo": "http://www.agency.gov/widget-data-standard/",
+        "describedBy": "http://www.agency.gov/widgets/schema.json",
+        "describedByType": "application/schema+json",
+        "description": "Widget data as a JSON feed",
+        "downloadURL": "http://www.agency.gov/feeds/widgets-all.json",
+        "format": "JSON",
+        "mediaType": "application/json",
+        "title": "widgets-all.json",
+        "@type": "dcat:Distribution"
+      },
+      {
+        "accessURL": "https://data.agency.gov/api/widgets-statistics/",
+        "description": "A fully queryable REST API with JSON and XML output",
+        "format": "API",
+        "title": "Widgets REST API",
+        "@type": "dcat:Distribution"
+      }
+    ],
+    "issued": "2011-11-22",
+    "landingPage": "http://agency.gov/widgets/data",
+    "language": ["en-US"],
+    "license": "http://creativecommons.org/publicdomain/zero/1.0/",
+    "primaryITInvestmentUII": "021-006227212",
+    "references": [
+      "http://agency.gov/docs/widgets-1.html",
+      "http://agency.gov/docs/widgets-2.html"
+    ],
+    "rights": "This dataset has been given an international public domain dedication for worldwide reuse",
+    "spatial": "United States",
+    "systemOfRecords": "http://www.agency.gov/widgets/sorn/",
+    "temporal": "2009-09-01T12:00:00Z/2010-05-31T12:00:00Z",
+    "theme": ["manufacturing"],
+    "@type": "dcat:Dataset"
+  }]
+}