Zum Inhalt
HALOWERK

Technische Prüfungen & Formate

F TD2000 DOCUMENTS 06 / pdf tounicode codespace bfchar bfrange utf16 text reconstruction

Reconstruct Unicode text and code-to-character boundaries from a supplied decoded PDF ToUnicode CMap.

POST https://detect.halowerk.com/v1/F-TD2000-DOCUMENTS-06/pdf-tounicode-codespace-bfchar-bfrange-utf16-text-reconstruction

Eingaben

Felder des veröffentlichten Eingabeschemas
FeldTypPflichtBeschreibung
artifactobjectJa
Vollständiges Eingabeschema anzeigen
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "artifact"
  ],
  "properties": {
    "artifact": {
      "type": "object",
      "additionalProperties": false,
      "required": [
        "pdfToUnicode"
      ],
      "properties": {
        "pdfToUnicode": {
          "type": "object",
          "additionalProperties": false,
          "required": [
            "data",
            "claim"
          ],
          "properties": {
            "data": {
              "type": "object",
              "additionalProperties": false,
              "required": [
                "code_spaces",
                "mappings",
                "bytes_hex"
              ],
              "properties": {
                "code_spaces": {
                  "type": "array",
                  "items": {
                    "type": "object",
                    "additionalProperties": false,
                    "required": [
                      "low",
                      "high"
                    ],
                    "properties": {
                      "low": {
                        "type": "string",
                        "maxLength": 8,
                        "minLength": 2,
                        "pattern": "^(?:[0-9A-Fa-f]{2})*$"
                      },
                      "high": {
                        "type": "string",
                        "maxLength": 8,
                        "minLength": 2,
                        "pattern": "^(?:[0-9A-Fa-f]{2})*$"
                      }
                    }
                  },
                  "maxItems": 16,
                  "minItems": 1
                },
                "mappings": {
                  "type": "array",
                  "items": {
                    "type": "object",
                    "additionalProperties": false,
                    "required": [
                      "kind",
                      "low",
                      "high",
                      "values"
                    ],
                    "properties": {
                      "kind": {
                        "enum": [
                          "char",
                          "range_array",
                          "range_increment"
                        ]
                      },
                      "low": {
                        "type": "string",
                        "maxLength": 8,
                        "minLength": 2,
                        "pattern": "^(?:[0-9A-Fa-f]{2})*$"
                      },
                      "high": {
                        "type": "string",
                        "maxLength": 8,
                        "minLength": 2,
                        "pattern": "^(?:[0-9A-Fa-f]{2})*$"
                      },
                      "values": {
                        "type": "array",
                        "items": {
                          "type": "string",
                          "maxLength": 1024,
                          "minLength": 4,
                          "pattern": "^(?:[0-9A-Fa-f]{2})*$"
                        },
                        "maxItems": 256,
                        "minItems": 1
                      }
                    }
                  },
                  "maxItems": 128,
                  "minItems": 1
                },
                "bytes_hex": {
                  "type": "string",
                  "maxLength": 4096,
                  "minLength": 0,
                  "pattern": "^(?:[0-9A-Fa-f]{2})*$"
                }
              }
            },
            "claim": {
              "anyOf": [
                {
                  "type": "null"
                },
                {
                  "type": "object",
                  "additionalProperties": false,
                  "required": [
                    "text",
                    "glyphs"
                  ],
                  "properties": {
                    "text": {
                      "type": "string",
                      "maxLength": 20000,
                      "minLength": 0
                    },
                    "glyphs": {
                      "type": "array",
                      "items": {
                        "type": "object",
                        "additionalProperties": false,
                        "required": [
                          "byte_offset",
                          "code_hex",
                          "unicode"
                        ],
                        "properties": {
                          "byte_offset": {
                            "type": "integer",
                            "minimum": 0,
                            "maximum": 2048
                          },
                          "code_hex": {
                            "type": "string",
                            "maxLength": 8,
                            "minLength": 2,
                            "pattern": "^(?:[0-9A-Fa-f]{2})*$"
                          },
                          "unicode": {
                            "type": "string",
                            "maxLength": 512,
                            "minLength": 0
                          }
                        }
                      },
                      "maxItems": 2048,
                      "minItems": 0
                    }
                  }
                }
              ]
            }
          }
        }
      }
    }
  }
}

Originalschema öffnen

Ergebnis & Dokumentation

Maschinenlesbare Dokumentation dieses Hubs

Quelle dieser Seite: der veröffentlichte HALOWERK-Katalog. Stand: 2026-11-01, 15:19 UTC.

Weitere Endpunkte dieses Hubs

Alle Endpunkte dieses Hubs →