JSON: implement pattern keys in schema

Jay Berkenbilt
1 parent 67d5ed3a
Showing 4 changed files with 51 additions and 7 deletions
libqpdf/JSON.cc
libtests/json.cc
libtests/qtest/json/json.out
manual/qpdf-manual.xml
@@ -323,6 +323,7 @@ JSON::checkSchemaInternal(JSON_value* this_v, JSON_value* sch_v,
         err_prefix = "json key \"" + prefix + "\"";
     }
+    std::string pattern_key;
     if (sch_dict)
     {
         if (! this_dict)
@@ -331,6 +332,31 @@ JSON::checkSchemaInternal(JSON_value* this_v, JSON_value* sch_v,
             errors.push_back(err_prefix + " is supposed to be a dictionary");
             return false;
         }
+        auto members = sch_dict->members;
+        std::string key;
+        if ((members.size() == 1) &&
+            ((key = members.begin()->first, key.length() > 2) &&
+             (key.at(0) == '<') &&
+             (key.at(key.length() - 1) == '>')))
+        {
+            pattern_key = key;
+        }
+    }
+
+    if (sch_dict && (! pattern_key.empty()))
+    {
+        auto pattern_schema = sch_dict->members[pattern_key].getPointer();
+        for (auto iter: this_dict->members)
+        {
+            std::string const& key = iter.first;
+            checkSchemaInternal(
+                this_dict->members[key].getPointer(),
+                pattern_schema,
+                errors, prefix + "." + key);
+        }
+    }
+    else if (sch_dict)
+    {
         for (std::map<std::string, PointerHolder<JSON_value> >::iterator iter =
                  sch_dict->members.begin();
              iter != sch_dict->members.end(); ++iter)
@@ -112,6 +112,11 @@ static void test_schema()
         "    >>"
         "  ]"
         ">>").getJSON();
+    JSON three = JSON::makeDictionary();
+    three.addDictionaryMember(
+        "<objid>",
+        QPDFObjectHandle::parse("<< /z (ebra) >>").getJSON());
+    schema.addDictionaryMember("/three", three);
     JSON a = QPDFObjectHandle::parse("[(not a) (dictionary)]").getJSON();
     check_schema(a, schema, false, "top-level type mismatch");
     JSON b = QPDFObjectHandle::parse(
@@ -142,8 +147,12 @@ static void test_schema()
         "      /glarp (4 enspliel)"
         "    >>"
         "  ]"
+        "  /three <<"
+        "    /anything << /x (oops) >>"
+        "    /else << /z (okay) >>"
+        "  >>"
         ">>").getJSON();
-    check_schema(b, schema, false, "top-level type mismatch");
+    check_schema(b, schema, false, "missing items");
     check_schema(a, a, false, "top-level schema array error");
     check_schema(b, b, false, "lower-level schema array error");
     check_schema(schema, schema, true, "pass");
 --- top-level type mismatch
 top-level object is supposed to be a dictionary
 ---
---- top-level type mismatch
+--- missing items
 json key "./one./a": key "/q" is present in schema but missing in object
 json key "./one./a./r" is supposed to be a dictionary
 json key "./one./a./s" is supposed to be an array
 json key "./one./a": key "/t" is not present in schema but appears in object
+json key "./three./anything": key "/z" is present in schema but missing in object
+json key "./three./anything": key "/x" is not present in schema but appears in object
 json key "./two.1": key "/glarp" is present in schema but missing in object
 json key "./two.1": key "/flarp" is not present in schema but appears in object
 json key "./two.2" is supposed to be a dictionary
@@ -3082,11 +3082,18 @@ outfile.pdf&lt;/option&gt;
         <itemizedlist>
          <listitem>
           <para>
-           A dictionary in the help output means that the corresponding
-           location in the actual JSON output is also a dictionary with
-           exactly the same keys; that is, no keys present in help are
-           absent in the real output, and no keys will be present in
-           the real output that are not in help.
+           A dictionary in the help output means that the
+           corresponding location in the actual JSON output is also a
+           dictionary with exactly the same keys; that is, no keys
+           present in help are absent in the real output, and no keys
+           will be present in the real output that are not in help. As
+           a special case, if the dictionary has a single key whose
+           name starts with <literal>&lt;</literal> and ends with
+           <literal>&gt;</literal>, it means that the JSON output is a
+           dictionary that can have any keys, each of which conforms
+           to the value of the special key. This is used for cases in
+           which the keys of the dictionary are things like object
+           IDs.
           </para>
          </listitem>
          <listitem>