SPB Git
2.2 KB · 94 lines yaml
1# Filing parsing configuration2parsing:3  html:4    parser: lxml5    remove_tags:6      - script7      - style8      - meta9      - link10    preserve_tables: true11    preserve_lists: true12    normalize_whitespace: true13    max_file_size_mb: 501415  sections:16    form_10k:17      - name: "business"18        item: "1"19        aliases: ["item 1", "item 1.", "item1"]20      - name: "risk_factors"21        item: "1A"22        aliases: ["item 1a", "item 1a.", "item1a"]23      - name: "unresolved_staff_comments"24        item: "1B"25        aliases: ["item 1b", "item 1b."]26      - name: "properties"27        item: "2"28        aliases: ["item 2", "item 2."]29      - name: "legal_proceedings"30        item: "3"31        aliases: ["item 3", "item 3."]32      - name: "mine_safety"33        item: "4"34        aliases: ["item 4", "item 4."]35      - name: "market_for_equity"36        item: "5"37        aliases: ["item 5", "item 5."]38      - name: "selected_financial_data"39        item: "6"40        aliases: ["item 6", "item 6."]41      - name: "md_and_a"42        item: "7"43        aliases: ["item 7", "item 7."]44      - name: "quantitative_disclosures"45        item: "7A"46        aliases: ["item 7a", "item 7a."]47      - name: "financial_statements"48        item: "8"49        aliases: ["item 8", "item 8."]50      - name: "changes_in_accounting"51        item: "9"52        aliases: ["item 9", "item 9."]53      - name: "controls_and_procedures"54        item: "9A"55        aliases: ["item 9a", "item 9a."]56      - name: "other_information"57        item: "9B"58        aliases: ["item 9b", "item 9b."]5960    form_10q:61      - name: "financial_statements"62        item: "1"63        part: 164      - name: "md_and_a"65        item: "2"66        part: 167      - name: "quantitative_disclosures"68        item: "3"69        part: 170      - name: "controls_and_procedures"71        item: "4"72        part: 173      - name: "legal_proceedings"74        item: "1"75        part: 276      - name: "risk_factors"77        item: "1A"78        part: 279      - name: "unregistered_sales"80        item: "2"81        part: 28283  chunking:84    strategy: sentence_window85    chunk_size: 51286    chunk_overlap: 6487    min_chunk_size: 5088    max_chunk_size: 102489    sentence_boundary: true9091  parallel:92    max_workers: 493    batch_size: 10094
Files · 2324b5870ae006e2244106d9aac3aef575817e38
Menu

Theme