mkvmerge: fix "playlist_file" type in JSON output

"playlist_file" must be an array of strings, not a single string. In verbose identification output mode this property has always been output multiple times. In JSON only one of those was actually output, the last one. Additionally the JSON schema didn't contain "playlist_file" at all.
2024-12-23 19:31:44 +00:00 · 2016-01-31 13:30:25 +01:00 · 2016-01-31 13:30:25 +01:00 · c9eb86f88d
commit c9eb86f88d
parent ddfb5cc92e
11 changed files with 390 additions and 12 deletions
--- a/7
+++ b/7
@ -1,3 +1,10 @@
+2016-01-31  Moritz Bunkus  <moritz@bunkus.org>
+
+        * mkvmerge: bug fix: fixed the output of the "playlist_file"
+        property of the "container" entity in the JSON identification
+        format from a single string to an array of strings. The format
+        version has been bumped to 3 due to this change.
+
 2016-01-30  Moritz Bunkus  <moritz@bunkus.org>

        * docs: added a Polish translation of the man pages by Daniel Kluz
--- a/doc/json-schema/mkvmerge-identification-output-schema-v3.json
+++ b/doc/json-schema/mkvmerge-identification-output-schema-v3.json
@ -0,0 +1,353 @@
+{
+  "$schema": "http://json-schema.org/draft-04/schema#",
+  "id": "https://mkvtoolnix.download/doc/mkvmerge-identification-output-schema-v3.json",
+  "title": "mkvmerge identification output",
+  "description": "The JSON output produced by mkvmerge's file identification mode",
+  "type": "object",
+  "properties": {
+    "attachments": {
+      "description": "an array describing the attachments found if any",
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "content_type": {
+            "type": "string",
+            "minLength": 1
+          },
+          "description": {
+            "type": "string"
+          },
+          "file_name": {
+            "type": "string"
+          },
+          "id": {
+            "type": "integer",
+            "minimum": 0
+          },
+          "size": {
+            "type": "integer",
+            "minimum": 0
+          },
+          "properties": {
+            "type": "object",
+            "properties": {
+              "uid": {
+                "type": "integer",
+                "minimum": 0
+              }
+            },
+            "additionalProperties": false
+          },
+          "type": {
+            "type": "string"
+          }
+        },
+        "additionalProperties": false,
+        "required": [
+          "file_name",
+          "id",
+          "properties",
+          "size"
+        ]
+      }
+    },
+    "chapters": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "num_entries": {
+            "type": "integer"
+          }
+        },
+        "additionalProperties": false,
+        "required": [
+          "num_entries"
+        ]
+      }
+    },
+    "container": {
+      "description": "information about the identified container",
+      "type": "object",
+      "properties": {
+        "properties": {
+          "description": "additional properties for the container varying by container format",
+          "type": "object",
+          "properties": {
+            "container_type": {
+              "description": "A unique number identifying the container type that's supposed to stay constant over all future releases of MKVToolNix",
+              "type": "integer",
+              "minLength": 1
+            },
+            "duration": {
+              "description": "The file's/segment's duration in nanoseconds",
+              "type": "integer",
+              "minimum": 0
+            },
+            "is_providing_timecodes": {
+              "description": "States whether or not the container has timestamps for the packets (e.g. Matroska, MP4) or not (e.g. SRT, MP3)",
+              "type": "boolean"
+            },
+            "segment_uid": {
+              "description": "A hexadecimal string of the segment's UID (only for Matroska files)",
+              "type": "string",
+              "minLength": 32,
+              "maxLength": 32
+            },
+            "next_segment_uid": {
+              "description": "A hexadecimal string of the next segment's UID (only for Matroska files)",
+              "type": "string",
+              "minLength": 32,
+              "maxLength": 32
+            },
+            "previous_segment_uid": {
+              "description": "A hexadecimal string of the previous segment's UID (only for Matroska files)",
+              "type": "string",
+              "minLength": 32,
+              "maxLength": 32
+            },
+            "other_file": {
+              "description": "The file name of an additional file processed as well",
+              "type": "string",
+              "minLength": 1
+            },
+            "playlist": {
+              "description": "States whether or not the identified file is a playlist (e.g. MPLS) referring to several other files",
+              "type": "boolean"
+            },
+            "playlist_chapters": {
+              "description": "The number of chapters in a playlist if it is a one",
+              "type": "integer",
+              "minimum": 0
+            },
+            "playlist_duration": {
+              "description": "The total duration in nanoseconds of all files referenced by the playlist if it is a one",
+              "type": "integer",
+              "minimum": 0
+            },
+            "playlist_file": {
+              "description": "An array of file names the playlist contains",
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            },
+            "playlist_size": {
+              "description": "The total size in bytes of all files referenced by the playlist if it is a one",
+              "type": "integer",
+              "minimum": 0
+            },
+            "title": {
+              "type": "string"
+            }
+          },
+          "additionalProperties": false
+        },
+        "recognized": {
+          "description": "States whether or not mkvmerge knows about the format",
+          "type": "boolean"
+        },
+        "supported": {
+          "description": "States whether or not mkvmerge can read the format",
+          "type": "boolean"
+        },
+        "type": {
+          "description": "A human-readable description/name for the container format",
+          "type": "string",
+          "minLength": 1
+        }
+      },
+      "additionalProperties": false,
+      "required": [
+        "recognized",
+        "supported"
+      ]
+    },
+    "errors": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "file_name": {
+      "description": "the identified file's name",
+      "type": "string",
+      "minLength": 1
+    },
+    "global_tags": {
+      "type": "array",
+      "items": {
+      }
+    },
+    "identification_format_version": {
+      "description": "The output format's version",
+      "type": "integer",
+      "minimum": 3,
+      "maximum": 3
+    },
+    "track_tags": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "num_entries": {
+            "type": "integer"
+          },
+          "track_id": {
+            "type": "integer"
+          }
+        },
+        "additionalProperties": false,
+        "required": [
+          "num_entries",
+          "track_id"
+        ]
+      }
+    },
+    "tracks": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "codec": {
+            "type": "string",
+            "minLength": 1
+          },
+          "id": {
+            "type": "integer",
+            "minLength": 0
+          },
+          "type": {
+            "type": "string"
+          },
+          "properties": {
+            "type": "object",
+            "properties": {
+              "aac_is_sbr": {
+                "type": "string",
+                "enum": [
+                  "true",
+                  "false",
+                  "unknown"
+                ]
+              },
+              "audio_bits_per_sample": {
+                "type": "integer",
+                "minimum": 0
+              },
+              "audio_channels": {
+                "type": "integer",
+                "minimum": 0
+              },
+              "audio_sampling_frequency": {
+                "type": "integer",
+                "minimum": 0
+              },
+              "codec_id": {
+                "type": "string"
+              },
+              "codec_private_data": {
+                "type": "string"
+              },
+              "codec_private_length": {
+                "type": "integer",
+                "minimum": 0
+              },
+              "content_encoding_algorithms": {
+                "type": "string",
+                "minLength": 1
+              },
+              "default_duration": {
+                "type": "integer",
+                "minimum": 0
+              },
+              "default_track": {
+                "type": "boolean"
+              },
+              "display_dimensions": {
+                "type": "string",
+                "pattern": "^[0-9]+x[0-9]+$"
+              },
+              "enabled_track": {
+                "type": "boolean"
+              },
+              "forced_track": {
+                "type": "boolean"
+              },
+              "language": {
+                "type": "string"
+              },
+              "number": {
+                "type": "integer",
+                "minimum": 0
+              },
+              "packetizer": {
+                "type": "string",
+                "minLength": 1
+              },
+              "pixel_dimensions": {
+                "type": "string",
+                "pattern": "^[0-9]+x[0-9]+$"
+              },
+              "stereo_mode": {
+                "type": "integer",
+                "minimum": 0
+              },
+              "stream_id": {
+                "type": "string",
+                "pattern": "^[0-9a-f]{2}$"
+              },
+              "sub_stream_id": {
+                "type": "string",
+                "pattern": "^[0-9a-f]{2}$"
+              },
+              "tag_artist": {
+                "type": "string"
+              },
+              "tag_bitsps": {
+                "type": "string"
+              },
+              "tag_bps": {
+                "type": "string"
+              },
+              "tag_fps": {
+                "type": "string"
+              },
+              "tag_title": {
+                "type": "string"
+              },
+              "text_subtitles": {
+                "type": "boolean"
+              },
+              "track_name": {
+                "type": "string"
+              },
+              "ts_pid": {
+                "type": "integer",
+                "minimum": 0
+              },
+              "uid": {
+                "type": "integer",
+                "minimum": 0
+              }
+            },
+            "additionalProperties": false
+          }
+        },
+        "additionalProperties": false,
+        "required": [
+          "codec",
+          "id",
+          "type"
+        ]
+      }
+    },
+    "warnings": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    }
+  }
+}
--- a/src/common/mm_mpls_multi_file_io.cpp
+++ b/src/common/mm_mpls_multi_file_io.cpp
@ -101,6 +101,10 @@ mm_mpls_multi_file_io_c::create_verbose_identification_info(mtx::id::info_c &inf
  info.add(mtx::id::playlist_duration, m_mpls_parser->get_playlist().duration.to_ns());
  info.add(mtx::id::playlist_size,     m_total_size);
  info.add(mtx::id::playlist_chapters, m_mpls_parser->get_chapters().size());
+
+  auto file_names = nlohmann::json::array();
  for (auto &file : m_files)
-    info.add(mtx::id::playlist_file, file.string());
+    file_names.push_back(file.string());
+
+  info.add(mtx::id::playlist_file, file_names);
 }
--- a/src/merge/generic_reader.cpp
+++ b/src/merge/generic_reader.cpp
@ -320,6 +320,13 @@ generic_reader_c::display_identification_results_as_text() {
    auto formatter = boost::format{"%1%:%2%"};

    for (auto const &pair : info) {
+      if (pair.second.is_array()) {
+        for (auto it = pair.second.begin(), end = pair.second.end(); it != end; ++it)
+          formatted.emplace_back((formatter % escape(pair.first) % escape(it->get<std::string>())).str());
+
+        continue;
+      }
+
      auto value = pair.second.is_number()  ? to_string(pair.second.get<uint64_t>())
                 : pair.second.is_boolean() ? std::string{pair.second.get<bool>() ? "1" : "0"}
                 :                            pair.second.get<std::string>();
@ -415,7 +422,7 @@ generic_reader_c::display_identification_results_as_json() {
  };

  auto json = nlohmann::json{
-    { "identification_format_version", 2                       },
+    { "identification_format_version", ID_JSON_FORMAT_VERSION  },
    { "file_name",                     m_ti.m_fname            },
    { "tracks",                        nlohmann::json::array() },
    { "attachments",                   nlohmann::json::array() },
--- a/src/merge/id_result.cpp
+++ b/src/merge/id_result.cpp
@ -33,8 +33,8 @@ static void
 output_container_unsupported_json(std::string const &filename,
                                  translatable_string_c const &info) {
  auto json = nlohmann::json{
-    { "identification_format_version", 2        },
-    { "file_name",                     filename },
+    { "identification_format_version", ID_JSON_FORMAT_VERSION },
+    { "file_name",                     filename               },
    { "container", {
        { "recognized", true                  },
        { "supported",  false                 },
--- a/src/merge/id_result.h
+++ b/src/merge/id_result.h
@ -27,6 +27,8 @@
 #define ID_RESULT_TAGS            "tags"
 #define ID_RESULT_GLOBAL_TAGS_ID  -1

+#define ID_JSON_FORMAT_VERSION    3
+
 struct id_result_t {
  int64_t id;
  std::string type, info, description;
--- a/src/merge/mkvmerge.cpp
+++ b/src/merge/mkvmerge.cpp
@ -369,8 +369,8 @@ list_file_types() {
 static void
 display_unsupported_file_type_json(filelist_t const &file) {
  auto json = nlohmann::json{
-    { "identification_format_version", 2         },
-    { "file_name",                     file.name },
+    { "identification_format_version", ID_JSON_FORMAT_VERSION },
+    { "file_name",                     file.name              },
    { "container", {
        { "recognized", false },
        { "supported",  false },
--- a/tests/results.txt
+++ b/tests/results.txt
@ -357,7 +357,7 @@ T_508splitting_by_parts_with_segment_linking:existence0-true-true-true-existence
 T_509rerender_track_headers_chapters_attachments:76712bb36be12e38e98a1342452f28d5:passed:20151115-230226:0.287840782
 T_510propedit_add_attachments_without_meta_seek_present:770103c238a0f502c9ec55f0599d8544:passed:20151121-101043:0.070892905
 T_511propedit_ensure_seek_head_exists_at_front:20f53afd94e39f5bbf3f1091eefbe31d:passed:20151129-194025:0.152563199
-T_512json_identification:dc56910afee27e5f42414fde294a262c+ok-4d5b44ce8fea381a4de100ed77ee77bc+ok-4ce52c415319a3c9ace3394b251bfa04+ok-b31447af73fb7453a6801f6817a5f904+ok-35d9a8927414617bce87deeeacb24a0b+ok-1d7e45d0520f72ac8cc40b4a31f62ce2+ok-7c4bfe1e467c782175892a155c9769aa+ok-2f1b1e7b1845e40b66c42c555e2214bd+ok-76d5c58b6fc06efcfea66e447ad8bf44+ok-4f84d928bfa74c33a5fd2f08f8e138b7+ok-8dd46981cf9e1787ea682fe03aba4d92+ok-e0fd5247650d9eee6a259b0a796cbcb0+ok-c56940a2497513380531e693ec06b76c+ok-ee1ae1f2602ebaef4e83772ab5e39804+ok-617e011e200630baff85bc674b2a1292+ok:passed:20151207-223859:6.280036064
+T_512json_identification:e2c1bd814ea805d9711a3875e646a51d+ok-d815a6390e25b861d21093ef66f17191+ok-19f449d85ad9c8c2a3d3840bc3734e58+ok-a86b43982a842c6b9c8572534e40dcca+ok-bf4664fb8aac8ad51e16d018d2c6697e+ok-e6e342718925ef84c9c65288d477ac76+ok-59c47f40f7c35d90a4a8ba0f15aebf5b+ok-b524a708c8e65517026daf4e18c6efcf+ok-eabca6419fcd27291e5db66c1e391c0d+ok-01f6792cb05fb5dd4823a5919a5565b4+ok-3f9fd90d34f591fa205eb235b1efe36c+ok-f7c9d7c612f38a0a2c0548a38008882f+ok-10bd29b4b37ba8e8fd746a45e67af4a1+ok-b137e5af83e68f2c52af9bfe3976a977+ok-c8b2bd3f66486fc47ad98d7b6a06f713+ok:passed:20151207-223859:1.876447112
 T_513vp9_10bit_key_frame_detection:9eab6e85ec792dcf670873d70a87f6ea:passed:20151208-224613:0.267556245
 T_514remove_track_statistics_tags_during_remux:43d4c0ec5cbbc31018715e62a99377df-afe190e36be530592fe3b83fb28d3e69-a7f246fe02132a1fb9cd3d7d0f85f180:passed:20151215-134129:1.426290351
 T_515aac_sampling_frequency_8000_is_not_sbr:b8f857faf759eae5362fefbb7cbeed23:passed:20151219-130357:0.066237884
@ -365,7 +365,7 @@ T_516hevc_rap_sample_grouping:bb42041df575edd35f36d47aebc341a7:passed:20151228-1
 T_517h264_forbidden_byte_sequence_in_slice_nalu:74e0fb1a25397078335c6d94974dc168:passed:20151228-134333:3.276176597
 T_518mlp:bc0269df9e0c0c968e4a408d7da46d35-0624d3f1975273199a0e12a9f4b0fd20:passed:20151229-134422:0.895368448
 T_519truehd:33f8c0f013c71529281179cf8669c567-33f8c0f013c71529281179cf8669c567:passed:20151229-135950:3.160459472
-T_520truehd_mlp_atmos_detection:790fe7a0cca6dfe0f4439fb36afd9d40+true-dc4a06c661033cb21e70bb25b661130a+true-565bc55dc9b15f81064785367040a978+true-93866c2e47b7aa3b8cf2483e8beb09ac+true-39d23fdc03248412b4bd364e51e4cf23+true-b41aaef4bd7e736256ff497be64e1e1f+true:passed:20151229-160649:5.913862696
+T_520truehd_mlp_atmos_detection:9337a350fa1e3451ff22b16afe0c770c+true-307f37e86e9df0245aca5908c0409c66+true-e1d9b0e42dc386b54916cfd8d6f6722b+true-531bd72e14816ccacd33202720f94544+true-12b89a0d1fe60bb5271bafbf1b34d275+true-01bcbc0330a73eb417d83c5576378466+true:passed:20151229-160649:2.357134495
 T_521mp4_edit_list_constant_offset_with_segment_duration_not_0:07984c40325903cbc35c8ae05dc86a72:passed:20151228-185646:0.621563048
 T_522mpeg_1_2_es_no_start_code_at_beginning:067554d94399178b6bb56b49746b04b6:passed:20151230-182435:0.299243222
 T_523mpeg_ts_pes_size_0:5351b2c74ad4327eeecee1ccf658ef5f-217f7e6e3e04a6afe253487af08c0598:passed:20151230-221825:1.635929691
--- a/tests/test-512json_identification.rb
+++ b/tests/test-512json_identification.rb
@ -26,15 +26,19 @@ test "identification and validation" do
  files.each do |file|
    output, _     = identify file, :format => :json
    output        = output.join ''
+    json          = JSON.load(output)

-    valid, errors = json_schema_identification.validate(JSON.load(output))
+    valid, errors = json_schema_identification.validate(json)

    if !valid
      puts " JSON validation errors in #{file}:"
      puts errors.join("\n")
    end

-    hashes << "#{output.md5}+#{valid ? "ok" : "invalid"}"
+    json.delete("identification_format_version")
+    json_md5 = JSON.dump(json).md5
+
+    hashes << "#{json_md5}+#{valid ? "ok" : "invalid"}"
  end

  hashes.join '-'
--- a/tests/test-520truehd_mlp_atmos_detection.rb
+++ b/tests/test-520truehd_mlp_atmos_detection.rb
@ -22,7 +22,8 @@ def verify520 file, track, codec

    end

-    "#{output.md5}+#{ok}"
+    json.delete("identification_format_version")
+    JSON.dump(json).md5 + "+#{ok}"
  end
 end

--- a/tests/test.d/simple_test.rb
+++ b/tests/test.d/simple_test.rb
@ -308,7 +308,7 @@ class SimpleTest
    json_store = JsonSchema::DocumentStore.new
    parser     = JsonSchema::Parser.new
    expander   = JsonSchema::ReferenceExpander.new
-    schema     = parser.parse JSON.load(File.read("../doc/json-schema/mkvmerge-identification-output-schema-v2.json"))
+    schema     = parser.parse JSON.load(File.read("../doc/json-schema/mkvmerge-identification-output-schema-v3.json"))

    expander.expand(schema, store: json_store)
    json_store.add_schema schema