Petr Polezhaev
b8f82607f9
- html_scraper: add img_alt strategy (НЭБ titles from <img alt>), bold_text strategy (Alib entries from <p><b>), Windows-1251 encoding support, _cls_inner_texts() helper that strips inner HTML tags - rsl: rewrite to POST SearchFilterForm[search] with CSRF token and CQL title:(words) AND author:(word) query format - config: update rusneb (img_alt + correct author_class) and alib_web (encoding + bold_text) to match fixed plugin strategies - tests: add tests/test_archives.py with network-marked tests for all six archive plugins; НЛР and ШПИЛ marked xfail (endpoints return HTTP 404) - presubmit: exclude network tests from default run (-m "not network") Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
104 lines
2.9 KiB
YAML
104 lines
2.9 KiB
YAML
# Function configurations — dict per category (not lists).
|
|
# AI functions reference a model from models.*.yaml.
|
|
# Archive functions specify a type and optional config dict.
|
|
# Keys within each category serve as plugin_id; must be unique across all categories.
|
|
# Override individual functions in functions.user.yaml.
|
|
functions:
|
|
# ── Boundary detection: image → {boundaries: [...], confidence: 0.x}
|
|
# ai_shelf_boundaries / ai_book_boundaries stored as {functionId: [fractions]} per entity.
|
|
boundary_detectors:
|
|
shelves: # key = plugin_id = target; runs on cabinet images
|
|
model: vl_detect_shelves
|
|
max_image_px: 1600
|
|
auto_queue: false
|
|
rate_limit_seconds: 0
|
|
timeout: 30
|
|
|
|
books: # key = plugin_id = target; runs on shelf images
|
|
model: vl_detect_books
|
|
max_image_px: 1600
|
|
auto_queue: false
|
|
rate_limit_seconds: 0
|
|
timeout: 30
|
|
|
|
# ── Text recognition: spine image → {raw_text, title, author, year, publisher, other}
|
|
text_recognizers:
|
|
recognize:
|
|
model: vl_recognize
|
|
max_image_px: 1600
|
|
auto_queue: true
|
|
rate_limit_seconds: 0
|
|
timeout: 30
|
|
|
|
# ── Book identification: raw_text → {title, author, year, isbn, publisher, confidence}
|
|
book_identifiers:
|
|
identify:
|
|
model: ai_identify
|
|
confidence_threshold: 0.8
|
|
auto_queue: false
|
|
rate_limit_seconds: 0
|
|
timeout: 30
|
|
|
|
# ── Archive searchers: query → [{source, title, author, year, isbn, publisher}, ...]
|
|
archive_searchers:
|
|
openlibrary:
|
|
name: "OpenLibrary"
|
|
type: openlibrary
|
|
auto_queue: true
|
|
rate_limit_seconds: 5
|
|
timeout: 8
|
|
|
|
rsl:
|
|
name: "РГБ"
|
|
type: rsl
|
|
auto_queue: true
|
|
rate_limit_seconds: 5
|
|
timeout: 8
|
|
|
|
rusneb:
|
|
name: "НЭБ"
|
|
type: html_scraper
|
|
auto_queue: true
|
|
rate_limit_seconds: 5
|
|
timeout: 8
|
|
config:
|
|
url: "https://rusneb.ru/search/"
|
|
search_param: q
|
|
img_alt: true
|
|
author_class: "search-list__item_subtext"
|
|
|
|
alib_web:
|
|
name: "Alib (web)"
|
|
type: html_scraper
|
|
auto_queue: false
|
|
rate_limit_seconds: 5
|
|
timeout: 8
|
|
config:
|
|
url: "https://www.alib.ru/find3.php4"
|
|
search_param: tfind
|
|
extra_params: {f: "5", s: "0"}
|
|
encoding: "cp1251"
|
|
bold_text: true
|
|
|
|
nlr:
|
|
name: "НЛР"
|
|
type: sru_catalog
|
|
auto_queue: false
|
|
rate_limit_seconds: 5
|
|
timeout: 8
|
|
config:
|
|
url: "http://www.nlr.ru/search/query"
|
|
query_prefix: "title="
|
|
|
|
shpl:
|
|
name: "ШПИЛ"
|
|
type: html_scraper
|
|
auto_queue: false
|
|
rate_limit_seconds: 5
|
|
timeout: 8
|
|
config:
|
|
url: "https://www.shpl.ru/cgi-bin/irbis64/cgiirbis_64.exe"
|
|
search_param: S21ALL
|
|
extra_params: {C21COM: S, I21DBN: BIBL, P21DBN: BIBL, S21FMT: briefWebRus, Z21ID: ""}
|
|
brief_class: "brief"
|