{ "$schema": "https://uipkge.dev/schema/registry-item.json", "name": "parquet-metadata-inspector", "title": "Parquet Metadata Inspector", "type": "registry:page", "files": [ { "path": "packages/registry-angular/blocks/parquet-metadata-inspector/parquet-metadata-inspector.component.ts", "content": "// Apache Parquet file deep-dive inspector: file header with S3 URI copy + header-JSON\n// copy/download, four telemetry cards, a row-group switcher banner, and a four-tab view\n// (column-chunk statistics with search + encoding filter, schema tree, dictionary metrics,\n// Thrift FileMetaData JSON). Consolidates the five Vue SFCs + data files 1:1; the data,\n// types and schema siblings are verbatim copies of the Vue sources.\nimport { ChangeDetectionStrategy, Component, Input, computed, signal } from '@angular/core'\nimport {\n ArrowRight,\n Binary,\n Check,\n Code2,\n Columns3,\n Copy,\n Download,\n FileCode2,\n FolderTree,\n HardDrive,\n Layers,\n LucideAngularModule,\n Search,\n Table2,\n} from 'lucide-angular'\nimport { cn } from '@/lib/utils'\nimport { UiBadgeComponent } from '@/ui/badge/badge.component'\nimport { UiButtonComponent } from '@/ui/button/button.component'\nimport {\n UiCardComponent,\n UiCardContentComponent,\n UiCardDescriptionComponent,\n UiCardHeaderComponent,\n UiCardTitleComponent,\n} from '@/ui/card/card.component'\nimport { UiProgressComponent } from '@/ui/progress/progress.component'\nimport {\n UiTableBodyComponent,\n UiTableCellComponent,\n UiTableComponent,\n UiTableHeadComponent,\n UiTableHeaderComponent,\n UiTableRowComponent,\n} from '@/ui/table/table.component'\nimport {\n UiTabsComponent,\n UiTabsContentComponent,\n UiTabsListComponent,\n UiTabsTriggerComponent,\n} from '@/ui/tabs/tabs.component'\nimport { defaultRowGroupsData, parquetHeaderJson } from './parquet-metadata-data'\nimport type { ColumnChunk, RowGroupMeta } from './parquet-metadata-types'\nimport { schemaTreeNodes, type SchemaTreeNode } from './parquet-schema'\n\nexport type { ColumnChunk, RowGroupMeta }\n\n@Component({\n changeDetection: ChangeDetectionStrategy.Eager,\n selector: 'ui-parquet-metadata-inspector, [ui-parquet-metadata-inspector]',\n standalone: true,\n // React renders the root
itself: the host stays out of layout and `class` goes to the root.\n host: { '[attr.class]': '\"contents\"' },\n imports: [\n LucideAngularModule,\n UiBadgeComponent,\n UiButtonComponent,\n UiCardComponent,\n UiCardContentComponent,\n UiCardDescriptionComponent,\n UiCardHeaderComponent,\n UiCardTitleComponent,\n UiProgressComponent,\n UiTableBodyComponent,\n UiTableCellComponent,\n UiTableComponent,\n UiTableHeadComponent,\n UiTableHeaderComponent,\n UiTableRowComponent,\n UiTabsComponent,\n UiTabsContentComponent,\n UiTabsListComponent,\n UiTabsTriggerComponent,\n ],\n template: `\n
\n \n
\n
\n
\n
\n
\n \n
\n

\n {{ filePath() }}\n

\n \n @if (copiedUri()) {\n \n } @else {\n \n }\n \n
\n\n
\n \n \n {{ formatSpec() }}\n \n \n Total Rows:\n {{ totalRows() }}\n \n \n {{ fileSize() }}\n ·\n {{ compressionRatio() }} Compression Ratio\n
\n
\n
\n\n
\n \n @if (copiedJson()) {\n \n } @else {\n \n }\n {{ copiedJson() ? 'JSON Copied' : 'Copy Header JSON' }}\n \n\n \n @if (!downloadingJson()) {\n \n } @else {\n \n }\n Download Parquet Header JSON\n \n
\n
\n \n\n
\n \n
\n
\n
\n
\n
\n \n \n
\n

Row Groups

\n
\n 2 Groups\n
\n
\n
\n
\n 2\n Row Groups\n
\n
\n
\n Chunk Partitioning:\n 125,000 rows / group\n
\n
\n
\n
\n\n
\n
\n
\n
\n \n \n
\n

Columns / Schema

\n
\n 14 Chunks\n
\n
\n
\n
\n 14\n Column Chunks\n
\n
\n
\n Nested Topology:\n 2 Structs · 1 List\n
\n
\n
\n
\n\n
\n
\n
\n
\n \n \n
\n

Uncompressed Size

\n
\n \n 3.88x Savings\n \n
\n
\n
\n
\n {{\n uncompressedSize()\n }}\n Raw\n
\n
\n
\n Snappy Footprint:\n {{ fileSize() }} (Saved 53.0 MB)\n
\n
\n
\n
\n\n
\n
\n
\n
\n \n \n
\n

Dictionary Encoding

\n
\n 85.7%\n
\n
\n
\n
\n 12 / 14\n Columns Encoded\n
\n
\n
\n Encoding Algorithms:\n RLE + PLAIN_DICT\n
\n
\n
\n \n \n\n \n
\n
\n
\n
\n Inspect Row Group:\n
\n @for (rg of rowGroups(); track rg.id) {\n \n }\n
\n
\n\n
\n Row Group Offset:\n {{\n activeRowGroup().fileOffset\n }}\n Raw Footprint:\n {{\n activeRowGroup().totalByteSize\n }}\n
\n
\n
\n
\n\n \n \n
\n \n \n \n \n \n \n\n @if (activeTab() === 'chunks') {\n
\n
\n \n \n
\n
\n \n \n Dict Encoded\n \n \n
\n
\n }\n
\n\n \n \n
\n
\n \n \n \n \n \n \n \n \n \n \n \n @for (col of filteredColumns(); track col.name) {\n \n \n \n \n \n \n \n }\n @if (filteredColumns().length === 0) {\n \n \n \n }\n \n
Column Name & TypeEncoding & CodecMin / Max Column StatisticsNull ValuesCompressed / Raw Footprint
\n
\n
\n {{ col.name }}\n ID: {{ col.fieldId }}\n
\n
\n \n {{ col.physicalType }}\n \n \n {{ col.logicalType }}\n
\n
\n 		\n
\n
\n @for (enc of col.encodings; track enc) {\n \n {{ enc }}\n \n }\n
\n
\n Codec:\n {{ col.compression }}\n
\n
\n 		\n
\n
\n Min:\n {{\n col.minStat\n }}\n
\n
\n Max:\n {{\n col.maxStat\n }}\n
\n
\n 		\n
\n
\n \n {{ col.nullCount }} nulls\n \n
\n

\n {{ col.nullPct }} of {{ col.numValues }} rows\n

\n
\n 		\n
\n
\n {{ col.compressedBytes }}\n / {{ col.uncompressedBytes }}\n
\n
\n \n
\n {{ col.compressionRatio }} saved\n Offset: {{ col.dataPageOffset }}\n
\n
\n
\n
\n No matching column chunks found for filter criteria.\n
\n
\n
\n \n\n \n \n
\n
\n
\n
\n

Parquet Schema Definition & Field Hierarchy

\n

\n Hierarchical view of logical schema nodes, repetition rules (REQUIRED, OPTIONAL, REPEATED), and\n maximum definition / repetition levels for column projection.\n

\n
\n
\n D: Def Level\n R: Rep Level\n
\n
\n
\n
\n
\n
\n
\n \n message schema\n Root Message\n
\n 14 column fields\n
\n\n @for (node of nodes(); track node.id) {\n \n
\n \n {{ node.depth === 0 ? '├─' : '└─' }}\n \n \n {{ node.name }}\n \n \n {{ node.repetition }}\n \n \n {{ node.physicalType }}\n \n \n \n {{ node.logicalType }}\n \n
\n\n
\n \n |\n max_rep:\n {{ node.repLevel }}\n
\n ID: {{ node.id }}\n
\n
\n }\n
\n \n \n \n\n \n \n
\n
\n
\n

Dictionary Optimization Impact

\n

\n Plain dictionary replaces repeated byte strings and integers with compact 3-bit to 16-bit dictionary\n index pointers.\n

\n
\n
\n
\n
\n Dictionary Enabled Columns:\n 6 / 8 Monitored\n
\n
\n Avg Space Reduction:\n 78.4%\n
\n
\n Dictionary Page Overhead:\n 0.34 MB total\n
\n
\n RLE Run Length Efficiency:\n Optimal\n
\n
\n\n
\n Compression Distribution by Codec:\n
\n
\n Snappy + RLE Dict\n 74.2%\n
\n \n
\n
\n
\n
\n\n
\n
\n \n \n \n \n \n \n \n \n \n \n \n @for (col of dictionaryColumns(); track col.name) {\n \n \n \n \n \n \n \n }\n \n
ColumnDistinct EntriesBit WidthDict Page OffsetSpace Savings
{{ col.name }}\n \n {{ col.dictEntries?.toLocaleString() }} values\n \n {{ col.bitWidth }} bits / row\n {{ col.dictPageOffset }}\n \n
\n \n {{ col.compressionRatio }}\n \n ({{ col.compressedBytes }})\n
\n
\n
\n
\n
\n \n\n \n \n
\n
\n
\n \n FileMetaData.thrift.json\n Thrift Compact Protocol\n
\n \n
\n\n \n 
{{ headerJson() }}
\n
\n \n \n \n \n \n `,\n})\nexport class UiParquetMetadataInspectorComponent {\n protected readonly ArrowRight = ArrowRight\n protected readonly Binary = Binary\n protected readonly Check = Check\n protected readonly Code2 = Code2\n protected readonly Columns3 = Columns3\n protected readonly Copy = Copy\n protected readonly Download = Download\n protected readonly FileCode2 = FileCode2\n protected readonly FolderTree = FolderTree\n protected readonly HardDrive = HardDrive\n protected readonly Layers = Layers\n protected readonly Search = Search\n protected readonly Table2 = Table2\n\n readonly filePath = signal('s3://lakehouse-gold/orders_2026_q3_part0042.parquet')\n readonly formatSpec = signal('Apache Parquet v2.10 · Snappy Compressed')\n readonly totalRows = signal('250,000 Rows')\n readonly fileSize = signal('18.4 MB')\n readonly compressionRatio = signal('74.2%')\n readonly uncompressedSize = signal('71.4 MB')\n readonly rowGroups = signal(defaultRowGroupsData.map((rg) => ({ ...rg, columns: [...rg.columns] })))\n\n @Input('filePath') set filePathAttr(v: string | undefined) {\n if (v !== undefined) this.filePath.set(v)\n }\n @Input('formatSpec') set formatSpecAttr(v: string | undefined) {\n if (v !== undefined) this.formatSpec.set(v)\n }\n @Input('totalRows') set totalRowsAttr(v: string | undefined) {\n if (v !== undefined) this.totalRows.set(v)\n }\n @Input('fileSize') set fileSizeAttr(v: string | undefined) {\n if (v !== undefined) this.fileSize.set(v)\n }\n @Input('compressionRatio') set compressionRatioAttr(v: string | undefined) {\n if (v !== undefined) this.compressionRatio.set(v)\n }\n @Input('uncompressedSize') set uncompressedSizeAttr(v: string | undefined) {\n if (v !== undefined) this.uncompressedSize.set(v)\n }\n @Input('rowGroups') set rowGroupsAttr(v: RowGroupMeta[] | undefined) {\n if (v !== undefined) this.rowGroups.set(v.map((rg) => ({ ...rg, columns: [...rg.columns] })))\n }\n @Input('class') className?: string\n\n readonly selectedRowGroup = signal(0)\n readonly activeTab = signal('chunks')\n readonly searchQuery = signal('')\n readonly encodingFilter = signal<'all' | 'dictionary' | 'plain'>('all')\n readonly copiedJson = signal(false)\n readonly copiedUri = signal(false)\n readonly downloadingJson = signal(false)\n\n protected readonly nodes = signal(schemaTreeNodes)\n\n readonly activeRowGroup = computed(() => {\n const groups = this.rowGroups()\n return groups[this.selectedRowGroup()] ?? groups[0]!\n })\n\n readonly filteredColumns = computed(() => {\n const query = this.searchQuery().trim().toLowerCase()\n return this.activeRowGroup().columns.filter((col) => {\n const matchesSearch =\n !query ||\n col.name.toLowerCase().includes(query) ||\n col.physicalType.toLowerCase().includes(query) ||\n col.logicalType.toLowerCase().includes(query) ||\n col.encodings.some((enc) => enc.toLowerCase().includes(query))\n const matchesEncoding =\n this.encodingFilter() === 'all' ||\n (this.encodingFilter() === 'dictionary' && col.isDictionaryEncoded) ||\n (this.encodingFilter() === 'plain' && !col.isDictionaryEncoded)\n return matchesSearch && matchesEncoding\n })\n })\n\n readonly dictionaryColumns = computed(() => this.activeRowGroup().columns.filter((col) => col.isDictionaryEncoded))\n\n headerJson(): string {\n return parquetHeaderJson\n }\n\n get rootClass(): string {\n return cn(\n 'bg-background text-foreground border-border w-full overflow-hidden rounded-xl border shadow-xs',\n this.className,\n )\n }\n\n rowGroupClass(id: number): string {\n return cn(\n 'cursor-pointer rounded-lg border px-3 py-1.5 text-xs font-medium transition-colors',\n this.selectedRowGroup() === id\n ? 'bg-primary/10 text-primary border-primary/30 shadow-xs'\n : 'bg-muted/40 text-muted-foreground hover:bg-muted hover:text-foreground border-transparent',\n )\n }\n\n encodingClass(filter: 'all' | 'dictionary' | 'plain'): string {\n return cn(\n 'cursor-pointer rounded px-2 py-1 transition-colors',\n this.encodingFilter() === filter\n ? 'bg-background text-foreground shadow-xs'\n : 'text-muted-foreground hover:text-foreground',\n )\n }\n\n nodeNameClass(isGroup?: boolean): string {\n return cn('truncate font-mono font-medium', isGroup ? 'text-primary font-bold' : 'text-foreground')\n }\n\n indentRem(depth: number): number {\n return Math.max(1, depth * 1.5 + 1)\n }\n\n copyJsonToClipboard(): void {\n if (typeof navigator !== 'undefined' && navigator.clipboard) {\n void navigator.clipboard.writeText(parquetHeaderJson)\n this.copiedJson.set(true)\n setTimeout(() => this.copiedJson.set(false), 2000)\n }\n }\n\n copyUriToClipboard(): void {\n if (typeof navigator !== 'undefined' && navigator.clipboard) {\n void navigator.clipboard.writeText(this.filePath())\n this.copiedUri.set(true)\n setTimeout(() => this.copiedUri.set(false), 2000)\n }\n }\n\n handleDownloadJson(): void {\n this.downloadingJson.set(true)\n setTimeout(() => {\n if (typeof document !== 'undefined') {\n const blob = new Blob([parquetHeaderJson], { type: 'application/json' })\n const url = URL.createObjectURL(blob)\n const a = document.createElement('a')\n a.href = url\n a.download = 'parquet-file-metadata.json'\n document.body.appendChild(a)\n a.click()\n document.body.removeChild(a)\n URL.revokeObjectURL(url)\n }\n this.downloadingJson.set(false)\n }, 400)\n }\n}\n", "type": "registry:page", "target": "~/src/app/components/blocks/parquet-metadata-inspector/parquet-metadata-inspector.component.ts" }, { "path": "packages/registry-angular/blocks/parquet-metadata-inspector/parquet-metadata-data.ts", "content": "import type { RowGroupMeta } from './parquet-metadata-types'\n\nexport const parquetHeaderJson = `{\n \"version\": 2,\n \"created_by\": \"parquet-mr version 1.13.1 (build e29fa2b)\",\n \"num_rows\": 250000,\n \"num_row_groups\": 2,\n \"file_size_bytes\": 19293798,\n \"uncompressed_bytes\": 74868326,\n \"compression_codec\": \"SNAPPY\",\n \"encryption_algorithm\": null,\n \"schema\": [\n { \"name\": \"schema\", \"num_children\": 10 },\n { \"name\": \"order_id\", \"type\": \"FIXED_LEN_BYTE_ARRAY\", \"type_length\": 16, \"repetition_type\": \"REQUIRED\", \"field_id\": 1, \"converted_type\": \"UUID\" },\n { \"name\": \"customer_id\", \"type\": \"INT64\", \"repetition_type\": \"REQUIRED\", \"field_id\": 2, \"converted_type\": \"INT_64\" },\n { \"name\": \"order_status\", \"type\": \"BYTE_ARRAY\", \"repetition_type\": \"OPTIONAL\", \"field_id\": 3, \"converted_type\": \"UTF8\" },\n { \"name\": \"gross_amount\", \"type\": \"FIXED_LEN_BYTE_ARRAY\", \"type_length\": 9, \"repetition_type\": \"REQUIRED\", \"field_id\": 4, \"converted_type\": \"DECIMAL\", \"scale\": 2, \"precision\": 18 },\n { \"name\": \"created_at\", \"type\": \"INT64\", \"repetition_type\": \"REQUIRED\", \"field_id\": 5, \"converted_type\": \"TIMESTAMP_MICROS\" },\n { \"name\": \"customer_metadata\", \"num_children\": 2, \"repetition_type\": \"OPTIONAL\", \"field_id\": 6 },\n { \"name\": \"loyalty_tier\", \"type\": \"BYTE_ARRAY\", \"repetition_type\": \"OPTIONAL\", \"field_id\": 7, \"converted_type\": \"UTF8\" },\n { \"name\": \"lifetime_orders\", \"type\": \"INT32\", \"repetition_type\": \"OPTIONAL\", \"field_id\": 8, \"converted_type\": \"INT_32\" },\n { \"name\": \"line_items\", \"num_children\": 1, \"repetition_type\": \"OPTIONAL\", \"field_id\": 9, \"converted_type\": \"LIST\" },\n { \"name\": \"list\", \"num_children\": 1, \"repetition_type\": \"REPEATED\" },\n { \"name\": \"element\", \"num_children\": 2, \"repetition_type\": \"REQUIRED\" },\n { \"name\": \"sku\", \"type\": \"BYTE_ARRAY\", \"repetition_type\": \"REQUIRED\", \"field_id\": 12, \"converted_type\": \"UTF8\" },\n { \"name\": \"quantity\", \"type\": \"INT32\", \"repetition_type\": \"REQUIRED\", \"field_id\": 13, \"converted_type\": \"INT_32\" },\n { \"name\": \"shipping_country\", \"type\": \"BYTE_ARRAY\", \"repetition_type\": \"OPTIONAL\", \"field_id\": 14, \"converted_type\": \"UTF8\" },\n { \"name\": \"discount_rate\", \"type\": \"FLOAT\", \"repetition_type\": \"OPTIONAL\", \"field_id\": 15 },\n { \"name\": \"fulfillment_node\", \"type\": \"BYTE_ARRAY\", \"repetition_type\": \"OPTIONAL\", \"field_id\": 16, \"converted_type\": \"UTF8\" }\n ],\n \"row_groups\": [\n {\n \"ordinal\": 0,\n \"num_rows\": 125000,\n \"total_byte_size\": 37434163,\n \"total_compressed_size\": 9646899,\n \"file_offset\": 4,\n \"columns_count\": 14\n },\n {\n \"ordinal\": 1,\n \"num_rows\": 125000,\n \"total_byte_size\": 37434163,\n \"total_compressed_size\": 9646899,\n \"file_offset\": 9646903,\n \"columns_count\": 14\n }\n ],\n \"key_value_metadata\": [\n { \"key\": \"org.apache.spark.sql.parquet.row.metadata\", \"value\": \"{\\\\\"type\\\\\":\\\\\"struct\\\\\",\\\\\"fields\\\\\":[...]}\" },\n { \"key\": \"writer.model.name\", \"value\": \"lakehouse-batch-pipeline-gold-orders\" },\n { \"key\": \"parquet.version\", \"value\": \"2.10.0\" }\n ]\n}`\n\nexport const defaultRowGroupsData: RowGroupMeta[] = [\n {\n id: 0,\n numRows: 125000,\n numRowsFormatted: '125,000 rows',\n totalByteSize: '35.7 MB',\n totalCompressedSize: '9.2 MB',\n compressionRatio: '74.2%',\n fileOffset: '0x00000004',\n columns: [\n {\n name: 'order_id',\n physicalType: 'FIXED_LEN_BYTE_ARRAY(16)',\n logicalType: 'UUID',\n fieldId: 1,\n encodings: ['PLAIN', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 0,\n nullPct: '0.0%',\n minStat: '001a4e21-9a7c-4821-bc10-1a29f8c00192',\n maxStat: 'ffe918b2-3c11-4fa0-8914-df7201bca908',\n uncompressedBytes: '4.8 MB',\n compressedBytes: '1.2 MB',\n compressionRatio: '75.0%',\n compressionPct: 75,\n isDictionaryEncoded: false,\n dictEntries: null,\n dictPageOffset: null,\n dataPageOffset: '0x00000020',\n bitWidth: null,\n },\n {\n name: 'customer_id',\n physicalType: 'INT64',\n logicalType: 'INTEGER(64, true)',\n fieldId: 2,\n encodings: ['PLAIN_DICTIONARY', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 0,\n nullPct: '0.0%',\n minStat: '10,001',\n maxStat: '994,210',\n uncompressedBytes: '3.2 MB',\n compressedBytes: '0.9 MB',\n compressionRatio: '71.9%',\n compressionPct: 71.9,\n isDictionaryEncoded: true,\n dictEntries: 54200,\n dictPageOffset: '0x00125000',\n dataPageOffset: '0x00140200',\n bitWidth: 16,\n },\n {\n name: 'order_status',\n physicalType: 'BYTE_ARRAY',\n logicalType: 'STRING (UTF8)',\n fieldId: 3,\n encodings: ['PLAIN_DICTIONARY', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 0,\n nullPct: '0.0%',\n minStat: \"'cancelled'\",\n maxStat: \"'shipped'\",\n uncompressedBytes: '1.8 MB',\n compressedBytes: '0.2 MB',\n compressionRatio: '88.9%',\n compressionPct: 88.9,\n isDictionaryEncoded: true,\n dictEntries: 5,\n dictPageOffset: '0x0021a400',\n dataPageOffset: '0x0021a480',\n bitWidth: 3,\n },\n {\n name: 'gross_amount',\n physicalType: 'FIXED_LEN_BYTE_ARRAY(9)',\n logicalType: 'DECIMAL(18, 2)',\n fieldId: 4,\n encodings: ['PLAIN_DICTIONARY', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 0,\n nullPct: '0.0%',\n minStat: '$4.50',\n maxStat: '$14,820.00',\n uncompressedBytes: '3.4 MB',\n compressedBytes: '0.8 MB',\n compressionRatio: '76.5%',\n compressionPct: 76.5,\n isDictionaryEncoded: true,\n dictEntries: 28450,\n dictPageOffset: '0x0023a100',\n dataPageOffset: '0x0026e000',\n bitWidth: 15,\n },\n {\n name: 'created_at',\n physicalType: 'INT64',\n logicalType: 'TIMESTAMP(MICROS, UTC)',\n fieldId: 5,\n encodings: ['DELTA_BINARY_PACKED', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 0,\n nullPct: '0.0%',\n minStat: '2026-07-01 00:00:00.124000',\n maxStat: '2026-07-26 23:59:58.910000',\n uncompressedBytes: '3.1 MB',\n compressedBytes: '0.7 MB',\n compressionRatio: '77.4%',\n compressionPct: 77.4,\n isDictionaryEncoded: false,\n dictEntries: null,\n dictPageOffset: null,\n dataPageOffset: '0x002e1000',\n bitWidth: null,\n },\n {\n name: 'shipping_country',\n physicalType: 'BYTE_ARRAY',\n logicalType: 'STRING (UTF8)',\n fieldId: 6,\n encodings: ['PLAIN_DICTIONARY', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 24,\n nullPct: '0.02%',\n minStat: \"'AE'\",\n maxStat: \"'US'\",\n uncompressedBytes: '1.6 MB',\n compressedBytes: '0.3 MB',\n compressionRatio: '81.2%',\n compressionPct: 81.2,\n isDictionaryEncoded: true,\n dictEntries: 48,\n dictPageOffset: '0x0034a000',\n dataPageOffset: '0x0034a240',\n bitWidth: 6,\n },\n {\n name: 'discount_rate',\n physicalType: 'FLOAT',\n logicalType: 'FLOAT(32)',\n fieldId: 7,\n encodings: ['PLAIN_DICTIONARY', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 0,\n nullPct: '0.0%',\n minStat: '0.00',\n maxStat: '0.35',\n uncompressedBytes: '1.5 MB',\n compressedBytes: '0.4 MB',\n compressionRatio: '73.3%',\n compressionPct: 73.3,\n isDictionaryEncoded: true,\n dictEntries: 12,\n dictPageOffset: '0x00390100',\n dataPageOffset: '0x00390180',\n bitWidth: 4,\n },\n {\n name: 'fulfillment_node',\n physicalType: 'BYTE_ARRAY',\n logicalType: 'STRING (UTF8)',\n fieldId: 8,\n encodings: ['PLAIN_DICTIONARY', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 82,\n nullPct: '0.07%',\n minStat: \"'wh-ap-east-1'\",\n maxStat: \"'wh-us-west-2'\",\n uncompressedBytes: '1.7 MB',\n compressedBytes: '0.3 MB',\n compressionRatio: '82.4%',\n compressionPct: 82.4,\n isDictionaryEncoded: true,\n dictEntries: 16,\n dictPageOffset: '0x003e4000',\n dataPageOffset: '0x003e4120',\n bitWidth: 4,\n },\n ],\n },\n {\n id: 1,\n numRows: 125000,\n numRowsFormatted: '125,000 rows',\n totalByteSize: '35.7 MB',\n totalCompressedSize: '9.2 MB',\n compressionRatio: '74.2%',\n fileOffset: '0x00933250',\n columns: [\n {\n name: 'order_id',\n physicalType: 'FIXED_LEN_BYTE_ARRAY(16)',\n logicalType: 'UUID',\n fieldId: 1,\n encodings: ['PLAIN', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 0,\n nullPct: '0.0%',\n minStat: '00021c90-410a-49bf-a870-19efbc441200',\n maxStat: 'fff8a910-1840-4221-a109-ccb001928371',\n uncompressedBytes: '4.8 MB',\n compressedBytes: '1.2 MB',\n compressionRatio: '75.0%',\n compressionPct: 75,\n isDictionaryEncoded: false,\n dictEntries: null,\n dictPageOffset: null,\n dataPageOffset: '0x00933270',\n bitWidth: null,\n },\n {\n name: 'customer_id',\n physicalType: 'INT64',\n logicalType: 'INTEGER(64, true)',\n fieldId: 2,\n encodings: ['PLAIN_DICTIONARY', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 0,\n nullPct: '0.0%',\n minStat: '10,042',\n maxStat: '995,800',\n uncompressedBytes: '3.2 MB',\n compressedBytes: '0.9 MB',\n compressionRatio: '71.9%',\n compressionPct: 71.9,\n isDictionaryEncoded: true,\n dictEntries: 53900,\n dictPageOffset: '0x00a58000',\n dataPageOffset: '0x00a73000',\n bitWidth: 16,\n },\n {\n name: 'order_status',\n physicalType: 'BYTE_ARRAY',\n logicalType: 'STRING (UTF8)',\n fieldId: 3,\n encodings: ['PLAIN_DICTIONARY', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 0,\n nullPct: '0.0%',\n minStat: \"'cancelled'\",\n maxStat: \"'shipped'\",\n uncompressedBytes: '1.8 MB',\n compressedBytes: '0.2 MB',\n compressionRatio: '88.9%',\n compressionPct: 88.9,\n isDictionaryEncoded: true,\n dictEntries: 5,\n dictPageOffset: '0x00b41000',\n dataPageOffset: '0x00b41080',\n bitWidth: 3,\n },\n {\n name: 'gross_amount',\n physicalType: 'FIXED_LEN_BYTE_ARRAY(9)',\n logicalType: 'DECIMAL(18, 2)',\n fieldId: 4,\n encodings: ['PLAIN_DICTIONARY', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 0,\n nullPct: '0.0%',\n minStat: '$3.90',\n maxStat: '$16,240.00',\n uncompressedBytes: '3.4 MB',\n compressedBytes: '0.8 MB',\n compressionRatio: '76.5%',\n compressionPct: 76.5,\n isDictionaryEncoded: true,\n dictEntries: 28120,\n dictPageOffset: '0x00b65000',\n dataPageOffset: '0x00b99000',\n bitWidth: 15,\n },\n {\n name: 'created_at',\n physicalType: 'INT64',\n logicalType: 'TIMESTAMP(MICROS, UTC)',\n fieldId: 5,\n encodings: ['DELTA_BINARY_PACKED', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 0,\n nullPct: '0.0%',\n minStat: '2026-07-27 00:00:01.002000',\n maxStat: '2026-08-21 14:28:00.000000',\n uncompressedBytes: '3.1 MB',\n compressedBytes: '0.7 MB',\n compressionRatio: '77.4%',\n compressionPct: 77.4,\n isDictionaryEncoded: false,\n dictEntries: null,\n dictPageOffset: null,\n dataPageOffset: '0x00c12000',\n bitWidth: null,\n },\n {\n name: 'shipping_country',\n physicalType: 'BYTE_ARRAY',\n logicalType: 'STRING (UTF8)',\n fieldId: 6,\n encodings: ['PLAIN_DICTIONARY', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 18,\n nullPct: '0.01%',\n minStat: \"'AE'\",\n maxStat: \"'US'\",\n uncompressedBytes: '1.6 MB',\n compressedBytes: '0.3 MB',\n compressionRatio: '81.2%',\n compressionPct: 81.2,\n isDictionaryEncoded: true,\n dictEntries: 48,\n dictPageOffset: '0x00c7b000',\n dataPageOffset: '0x00c7b240',\n bitWidth: 6,\n },\n {\n name: 'discount_rate',\n physicalType: 'FLOAT',\n logicalType: 'FLOAT(32)',\n fieldId: 7,\n encodings: ['PLAIN_DICTIONARY', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 0,\n nullPct: '0.0%',\n minStat: '0.00',\n maxStat: '0.35',\n uncompressedBytes: '1.5 MB',\n compressedBytes: '0.4 MB',\n compressionRatio: '73.3%',\n compressionPct: 73.3,\n isDictionaryEncoded: true,\n dictEntries: 12,\n dictPageOffset: '0x00cc1000',\n dataPageOffset: '0x00cc1080',\n bitWidth: 4,\n },\n {\n name: 'fulfillment_node',\n physicalType: 'BYTE_ARRAY',\n logicalType: 'STRING (UTF8)',\n fieldId: 8,\n encodings: ['PLAIN_DICTIONARY', 'RLE'],\n compression: 'Snappy',\n numValues: '125,000',\n nullCount: 64,\n nullPct: '0.05%',\n minStat: \"'wh-ap-east-1'\",\n maxStat: \"'wh-us-west-2'\",\n uncompressedBytes: '1.7 MB',\n compressedBytes: '0.3 MB',\n compressionRatio: '82.4%',\n compressionPct: 82.4,\n isDictionaryEncoded: true,\n dictEntries: 16,\n dictPageOffset: '0x00d15000',\n dataPageOffset: '0x00d15120',\n bitWidth: 4,\n },\n ],\n },\n]\n", "type": "registry:page", "target": "~/src/app/components/blocks/parquet-metadata-inspector/parquet-metadata-data.ts" }, { "path": "packages/registry-angular/blocks/parquet-metadata-inspector/parquet-metadata-types.ts", "content": "export interface ColumnChunk {\n name: string\n physicalType: string\n logicalType: string\n fieldId: number\n encodings: string[]\n compression: string\n numValues: string\n nullCount: number\n nullPct: string\n minStat: string\n maxStat: string\n uncompressedBytes: string\n compressedBytes: string\n compressionRatio: string\n compressionPct: number\n isDictionaryEncoded: boolean\n dictEntries: number | null\n dictPageOffset: string | null\n dataPageOffset: string\n bitWidth: number | null\n}\n\nexport interface RowGroupMeta {\n id: number\n numRows: number\n numRowsFormatted: string\n totalByteSize: string\n totalCompressedSize: string\n compressionRatio: string\n fileOffset: string\n columns: ColumnChunk[]\n}\n", "type": "registry:page", "target": "~/src/app/components/blocks/parquet-metadata-inspector/parquet-metadata-types.ts" }, { "path": "packages/registry-angular/blocks/parquet-metadata-inspector/parquet-schema.ts", "content": "export interface SchemaTreeNode {\n id: number\n path: string\n name: string\n repetition: 'REQUIRED' | 'OPTIONAL' | 'REPEATED'\n physicalType: string\n logicalType: string\n defLevel: number\n repLevel: number\n depth: number\n isGroup?: boolean\n description: string\n}\n\nexport const schemaTreeNodes: SchemaTreeNode[] = [\n {\n id: 1,\n path: 'schema.order_id',\n name: 'order_id',\n repetition: 'REQUIRED',\n physicalType: 'FIXED_LEN_BYTE_ARRAY(16)',\n logicalType: 'UUID',\n defLevel: 0,\n repLevel: 0,\n depth: 0,\n description: 'Unique RFC 4122 order identifier binary token.',\n },\n {\n id: 2,\n path: 'schema.customer_id',\n name: 'customer_id',\n repetition: 'REQUIRED',\n physicalType: 'INT64',\n logicalType: 'INTEGER(64, true)',\n defLevel: 0,\n repLevel: 0,\n depth: 0,\n description: 'Foreign purchaser identity key.',\n },\n {\n id: 3,\n path: 'schema.order_status',\n name: 'order_status',\n repetition: 'OPTIONAL',\n physicalType: 'BYTE_ARRAY',\n logicalType: 'STRING (UTF8)',\n defLevel: 1,\n repLevel: 0,\n depth: 0,\n description: 'Lifecycle transition stage enumerated string.',\n },\n {\n id: 4,\n path: 'schema.gross_amount',\n name: 'gross_amount',\n repetition: 'REQUIRED',\n physicalType: 'FIXED_LEN_BYTE_ARRAY(9)',\n logicalType: 'DECIMAL(18, 2)',\n defLevel: 0,\n repLevel: 0,\n depth: 0,\n description: 'High-precision billing total charge with 2 scale points.',\n },\n {\n id: 5,\n path: 'schema.created_at',\n name: 'created_at',\n repetition: 'REQUIRED',\n physicalType: 'INT64',\n logicalType: 'TIMESTAMP(MICROS, UTC)',\n defLevel: 0,\n repLevel: 0,\n depth: 0,\n description: 'UTC microsecond epoch transaction timestamp.',\n },\n {\n id: 6,\n path: 'schema.customer_metadata',\n name: 'customer_metadata',\n repetition: 'OPTIONAL',\n physicalType: 'GROUP',\n logicalType: 'STRUCT',\n defLevel: 1,\n repLevel: 0,\n depth: 0,\n isGroup: true,\n description: 'Nested profile attributes struct.',\n },\n {\n id: 7,\n path: 'schema.customer_metadata.loyalty_tier',\n name: 'loyalty_tier',\n repetition: 'OPTIONAL',\n physicalType: 'BYTE_ARRAY',\n logicalType: 'STRING (UTF8)',\n defLevel: 2,\n repLevel: 0,\n depth: 1,\n description: 'Customer loyalty tier status membership level.',\n },\n {\n id: 8,\n path: 'schema.customer_metadata.lifetime_orders',\n name: 'lifetime_orders',\n repetition: 'OPTIONAL',\n physicalType: 'INT32',\n logicalType: 'INTEGER(32, true)',\n defLevel: 2,\n repLevel: 0,\n depth: 1,\n description: 'Cumulative prior purchases count.',\n },\n {\n id: 9,\n path: 'schema.line_items',\n name: 'line_items',\n repetition: 'OPTIONAL',\n physicalType: 'GROUP',\n logicalType: 'LIST',\n defLevel: 1,\n repLevel: 0,\n depth: 0,\n isGroup: true,\n description: '3-level Parquet Standard list layout.',\n },\n {\n id: 10,\n path: 'schema.line_items.list',\n name: 'list',\n repetition: 'REPEATED',\n physicalType: 'GROUP',\n logicalType: 'BAG',\n defLevel: 2,\n repLevel: 1,\n depth: 1,\n isGroup: true,\n description: 'Repeated list item wrapper group.',\n },\n {\n id: 11,\n path: 'schema.line_items.list.element',\n name: 'element',\n repetition: 'REQUIRED',\n physicalType: 'GROUP',\n logicalType: 'STRUCT',\n defLevel: 2,\n repLevel: 1,\n depth: 2,\n isGroup: true,\n description: 'Item tuple struct.',\n },\n {\n id: 12,\n path: 'schema.line_items.list.element.sku',\n name: 'sku',\n repetition: 'REQUIRED',\n physicalType: 'BYTE_ARRAY',\n logicalType: 'STRING (UTF8)',\n defLevel: 2,\n repLevel: 1,\n depth: 3,\n description: 'Stock keeping unit barcode tag.',\n },\n {\n id: 13,\n path: 'schema.line_items.list.element.quantity',\n name: 'quantity',\n repetition: 'REQUIRED',\n physicalType: 'INT32',\n logicalType: 'INTEGER(32, true)',\n defLevel: 2,\n repLevel: 1,\n depth: 3,\n description: 'Purchased quantity count.',\n },\n {\n id: 14,\n path: 'schema.shipping_country',\n name: 'shipping_country',\n repetition: 'OPTIONAL',\n physicalType: 'BYTE_ARRAY',\n logicalType: 'STRING (UTF8)',\n defLevel: 1,\n repLevel: 0,\n depth: 0,\n description: 'ISO-3166-1 alpha-2 destination country.',\n },\n {\n id: 15,\n path: 'schema.discount_rate',\n name: 'discount_rate',\n repetition: 'OPTIONAL',\n physicalType: 'FLOAT',\n logicalType: 'FLOAT(32)',\n defLevel: 1,\n repLevel: 0,\n depth: 0,\n description: 'Promotional discount multiplier applied.',\n },\n {\n id: 16,\n path: 'schema.fulfillment_node',\n name: 'fulfillment_node',\n repetition: 'OPTIONAL',\n physicalType: 'BYTE_ARRAY',\n logicalType: 'STRING (UTF8)',\n defLevel: 1,\n repLevel: 0,\n depth: 0,\n description: 'Assigned logistics warehouse cluster.',\n },\n]\n", "type": "registry:page", "target": "~/src/app/components/blocks/parquet-metadata-inspector/parquet-schema.ts" }, { "path": "packages/registry-angular/blocks/parquet-metadata-inspector/index.ts", "content": "export { UiParquetMetadataInspectorComponent } from './parquet-metadata-inspector.component'\nexport type { ColumnChunk, RowGroupMeta } from './parquet-metadata-types'\nexport type { SchemaTreeNode } from './parquet-schema'\n", "type": "registry:page", "target": "~/src/app/components/blocks/parquet-metadata-inspector/index.ts" } ], "dependencies": [ "lucide-angular" ], "devDependencies": [], "registryDependencies": [ "https://uipkge.dev/r/angular/badge.json", "https://uipkge.dev/r/angular/button.json", "https://uipkge.dev/r/angular/card.json", "https://uipkge.dev/r/angular/progress.json", "https://uipkge.dev/r/angular/table.json", "https://uipkge.dev/r/angular/tabs.json" ], "description": "Apache Parquet file format deep-dive inspector with telemetry overview, row groups switcher, column chunk statistics, dictionary encoding metrics, and hierarchical schema tree with repetition and definition levels.", "categories": [ "devops", "app" ] }