diff --git a/backend/scripts/smoke_references.py b/backend/scripts/smoke_references.py index 26c057c..55cebb0 100644 --- a/backend/scripts/smoke_references.py +++ b/backend/scripts/smoke_references.py @@ -15,6 +15,12 @@ The order of the first two steps is the point of the tag library rather than an accident of the script: **tags are made first and applied second**. A reference is created *with* tag ids, never with tag names, so a typo cannot invent a label — which is what step 4 checks. + +**Every entry this script creates carries a token in its title, its author and +its tag names.** The library it runs against is a real one and may hold hundreds +of entries, so "the search found one row" is only a meaningful assertion about +rows this run made. The token is what makes each count below a statement about +this run rather than about the library's size. """ from __future__ import annotations @@ -24,10 +30,21 @@ import sys import urllib.error import urllib.parse import urllib.request +import uuid from typing import Any BASE = "http://127.0.0.1:8000/api" +#: Stamped into every entry this run creates, so each search below can be scoped +#: to this run instead of to an empty database. Short and uppercase: it travels +#: in titles, in an author name and in tag names, and shows up in failure output. +TOKEN = uuid.uuid4().hex[:6].upper() + +#: A second token, carried by one contributor's *name* only. Titles and tag names +#: carry ``TOKEN``, so searching for it finds every row this run made; finding a +#: single row by author needs a string that is in exactly one place. +AUTHOR_TOKEN = f"AU{TOKEN}" + _checks = 0 @@ -73,11 +90,19 @@ def main() -> int: survey = call( "POST", "/reference-tags", - {"name": " 综述 ", "color": "rgb(64, 158, 255)", "note": "综述性文献"}, + { + "name": f" 综述-{TOKEN} ", + "color": "rgb(64, 158, 255)", + "note": "综述性文献", + }, expect=201, ) created_tags.append(survey["id"]) - check("a name is trimmed to one spelling", survey["name"] == "综述", survey["name"]) + check( + "a name is trimmed to one spelling", + survey["name"] == f"综述-{TOKEN}", + survey["name"], + ) check( "a colour is canonicalised", survey["color"] == "#409EFF", @@ -88,18 +113,27 @@ def main() -> int: must_read = call( "POST", "/reference-tags", - {"name": "必读", "color": "#f56c6c"}, + {"name": f"必读-{TOKEN}", "color": "#f56c6c"}, expect=201, ) created_tags.append(must_read["id"]) - check("the second tag is stored", must_read["name"] == "必读") + check("the second tag is stored", must_read["name"] == f"必读-{TOKEN}") print("2. a tag name is unique, and only a real colour is accepted") duplicate = call( - "POST", "/reference-tags", {"name": "综述"}, expect=409 + "POST", "/reference-tags", {"name": f"综述-{TOKEN}"}, expect=409 + ) + check( + "the refusal names the label", + TOKEN in duplicate["detail"], + duplicate["detail"], + ) + call( + "POST", + "/reference-tags", + {"name": f"怪颜色-{TOKEN}", "color": "blue"}, + expect=422, ) - check("the refusal names the label", "综述" in duplicate["detail"], duplicate["detail"]) - call("POST", "/reference-tags", {"name": "怪颜色", "color": "blue"}, expect=422) call("POST", "/reference-tags", {"name": " "}, expect=422) check("a blank name and a non-colour are refused", True) @@ -109,7 +143,7 @@ def main() -> int: "/references", { "type": "journal-article", - "title": "技术惯性与冲量的耦合机制", + "title": f"技术惯性与冲量的耦合机制({TOKEN})", "subtitle": "基于科学与技术融合网络的实证分析", "title_translated": "Coupling inertia and impulse in technology evolution", "container_title": "Technological Forecasting and Social Change", @@ -126,7 +160,11 @@ def main() -> int: "authors": [ {"name": "张三", "family_name": "张", "given_name": "三"}, {"name": "李四"}, - {"name": "Wang Wu", "family_name": "Wang", "given_name": "Wu"}, + { + "name": f"Wang Wu {AUTHOR_TOKEN}", + "family_name": "Wang", + "given_name": "Wu", + }, {"name": "世界卫生组织", "role": "compiler"}, ], }, @@ -137,7 +175,8 @@ def main() -> int: check("four contributors stored", len(article["authors"]) == 4) check( "they keep the order they were sent in", - [a["name"] for a in article["authors"]] == ["张三", "李四", "Wang Wu", "世界卫生组织"], + [a["name"] for a in article["authors"]] + == ["张三", "李四", f"Wang Wu {AUTHOR_TOKEN}", "世界卫生组织"], str([a["name"] for a in article["authors"]]), ) check( @@ -151,7 +190,8 @@ def main() -> int: check("not cited yet", article["citation_count"] == 0) check( "both tags are on the row", - sorted(tag["name"] for tag in article["tags"]) == ["必读", "综述"], + sorted(tag["name"] for tag in article["tags"]) + == [f"必读-{TOKEN}", f"综述-{TOKEN}"], str(article["tags"]), ) @@ -159,11 +199,15 @@ def main() -> int: missing_tag = call( "POST", "/references", - {"title": "引用了不存在的标签", "type": "book", "tag_ids": [999999]}, + { + "title": f"引用了不存在的标签{TOKEN}", + "type": "book", + "tag_ids": [999999], + }, expect=400, ) check("the refusal names the id", "999999" in missing_tag["detail"], missing_tag["detail"]) - orphan = call("GET", "/references?keyword=引用了不存在的标签") + orphan = call("GET", f"/references?keyword=引用了不存在的标签{TOKEN}") check("nothing was stored half-labelled", orphan["total"] == 0, str(orphan["total"])) print("5. add a patent, which needs a country and a number") @@ -172,7 +216,7 @@ def main() -> int: "/references", { "type": "patent", - "title": "一种基于多层聚类的人工智能技术识别方法", + "title": f"一种基于多层聚类的人工智能技术识别方法({TOKEN})", "patent_country": "中国", "patent_number": "CN114000000A", "publication_year": 2023, @@ -185,7 +229,7 @@ def main() -> int: check("patent stored", patent["type"] == "patent" and patent["patent_number"] == "CN114000000A") check( "tagging works on create for more than one entry", - [tag["name"] for tag in patent["tags"]] == ["必读"], + [tag["name"] for tag in patent["tags"]] == [f"必读-{TOKEN}"], str(patent["tags"]), ) @@ -204,28 +248,40 @@ def main() -> int: call( "POST", "/references", - {"title": "没有标签的书", "authors": [{"name": "甲"}], "type": "book"}, + { + "title": f"没有标签的书{TOKEN}", + "authors": [{"name": "甲"}], + "type": "book", + }, expect=201, ) - probe = call("GET", "/references?keyword=没有标签的书") + probe = call("GET", f"/references?keyword=没有标签的书{TOKEN}") created_references.append(probe["items"][0]["id"]) check("a book needs nothing else", probe["total"] == 1) check("and may carry no tags at all", probe["items"][0]["tags"] == []) print("8. find it again: by author, by type, by year, by tag") - by_author = call("GET", "/references?keyword=Wang") - check("search matches an author name", by_author["total"] == 1, str(by_author["total"])) + by_author = call("GET", f"/references?keyword={AUTHOR_TOKEN}") + check( + "search matches an author name", + by_author["total"] == 1, + f'{by_author["total"]} (the token is on one author name)', + ) check( "the row prints an author line", by_author["items"][0]["authors_line"].startswith("张三, 李四, Wang Wu"), by_author["items"][0]["authors_line"], ) - by_type = call("GET", "/references?type=patent") + by_type = call("GET", f"/references?type=patent&keyword={TOKEN}") check("filter by type", by_type["total"] == 1, str(by_type["total"])) - by_year = call("GET", "/references?year=2024") + by_year = call("GET", f"/references?year=2024&keyword={TOKEN}") check("filter by year", by_year["total"] == 1, str(by_year["total"])) - uncited = call("GET", "/references?cited=false") - check("filter by not-yet-cited", uncited["total"] == len(created_references)) + uncited = call("GET", f"/references?cited=false&keyword={TOKEN}") + check( + "filter by not-yet-cited", + uncited["total"] == len(created_references), + f'{uncited["total"]} of {len(created_references)}', + ) by_tag = call("GET", f"/references?tag={must_read['id']}") check("filter by tag", by_tag["total"] == 2, str(by_tag["total"])) @@ -240,31 +296,43 @@ def main() -> int: ) print("9. the tag table counts what carries each label") - tags = call("GET", "/reference-tags") + tags = call("GET", f"/reference-tags?keyword={TOKEN}") counts = {tag["name"]: tag["reference_count"] for tag in tags["items"]} - check("two labels in the library", tags["total"] == 2, str(tags["total"])) - check("the shared label counts two rows", counts["必读"] == 2, str(counts)) - check("the other counts one", counts["综述"] == 1, str(counts)) - found = call("GET", "/reference-tags?keyword=综述") + check("two labels carry this run's token", tags["total"] == 2, str(tags["total"])) + check( + "the shared label counts two rows", + counts[f"必读-{TOKEN}"] == 2, + str(counts), + ) + check("the other counts one", counts[f"综述-{TOKEN}"] == 1, str(counts)) + found = call("GET", f"/reference-tags?keyword=综述-{TOKEN}") check("tags are searchable by name", found["total"] == 1, str(found["total"])) print("10. renaming a label follows it everywhere it is used") renamed = call( "PATCH", f"/reference-tags/{survey['id']}", - {"name": "综述文章", "note": "综述与述评"}, + {"name": f"综述文章-{TOKEN}", "note": "综述与述评"}, ) - check("the label is renamed", renamed["name"] == "综述文章") + check("the label is renamed", renamed["name"] == f"综述文章-{TOKEN}") after = call("GET", f"/references/{article['id']}") check( "the reference prints the new name", - sorted(tag["name"] for tag in after["tags"]) == ["必读", "综述文章"], + sorted(tag["name"] for tag in after["tags"]) + == [f"必读-{TOKEN}", f"综述文章-{TOKEN}"], str(after["tags"]), ) taken = call( - "PATCH", f"/reference-tags/{survey['id']}", {"name": "必读"}, expect=409 + "PATCH", + f"/reference-tags/{survey['id']}", + {"name": f"必读-{TOKEN}"}, + expect=409, + ) + check( + "renaming onto a taken name is refused", + TOKEN in taken["detail"], + taken["detail"], ) - check("renaming onto a taken name is refused", "必读" in taken["detail"], taken["detail"]) print("11. edit it: replace the contributor list, a field and its tags") updated = call( @@ -283,7 +351,7 @@ def main() -> int: check("author list replaced wholesale", len(updated["authors"]) == 2) check( "tag list replaced wholesale too", - [tag["name"] for tag in updated["tags"]] == ["必读"], + [tag["name"] for tag in updated["tags"]] == [f"必读-{TOKEN}"], str(updated["tags"]), ) check("untouched fields kept", updated["container_title"] == "Technological Forecasting and Social Change") @@ -291,7 +359,7 @@ def main() -> int: cleared = call("PATCH", f"/references/{patent['id']}", {"tag_ids": None}) check( "omitting tags leaves them alone", - [tag["name"] for tag in cleared["tags"]] == ["必读"], + [tag["name"] for tag in cleared["tags"]] == [f"必读-{TOKEN}"], str(cleared["tags"]), ) @@ -300,7 +368,10 @@ def main() -> int: paper = call( "POST", "/papers", - {"title": "参考文献冒烟测试论文", "template_id": templates[0]["id"]}, + { + "title": f"参考文献冒烟测试论文{TOKEN}", + "template_id": templates[0]["id"], + }, expect=201, ) created_papers.append(paper["id"]) @@ -338,7 +409,7 @@ def main() -> int: check("and the paper", citations[0]["paper_id"] == paper["id"]) check("and the paragraph heading", citations[0]["paragraph_name"] is not None, str(citations[0])) - cited = call("GET", "/references?cited=true") + cited = call("GET", f"/references?cited=true&keyword={TOKEN}") check("the cited filter now finds it", cited["total"] == 1, str(cited["total"])) print("14. a cited reference cannot be deleted; an uncited one can") @@ -361,7 +432,25 @@ def main() -> int: str(left["total"]), ) - print("16. clean up") + print("16. the 参考文献 list prints one entry per work, in Springer style") + document = call("GET", f"/papers/{paper['id']}/document") + check("the style is named in the response", document["reference_style"] == "springer") + check( + "one entry for the one work cited", + len(document["references"]) == 1, + str(len(document["references"])), + ) + entry = document["references"][0] + check("the entry is a bibliography line", entry["text"].startswith("张三, 李四"), entry["text"]) + check("and carries the year and the DOI", "(2024)" in entry["text"] and "https://doi.org/10.1016/j.techfore.2024.123456" in entry["text"], entry["text"]) + check("it names the places it is cited", len(entry["citations"]) == 1, str(len(entry["citations"]))) + check( + "and the in-text marker is that entry's number", + entry["citations"][0]["index"] == entry["index"], + f'{entry["citations"][0]["index"]} vs {entry["index"]}', + ) + + print("17. clean up") call("DELETE", f"/papers/{paper['id']}", expect=204) created_papers.clear() for reference_id in created_references: @@ -370,13 +459,13 @@ def main() -> int: for tag_id in created_tags: call("DELETE", f"/reference-tags/{tag_id}", expect=204) created_tags.clear() - remaining = call("GET", "/references") + # Scoped by the token rather than by "the library is empty": the library + # this runs against holds real literature, and what must be true is that + # none of *this run's* rows survive. + remaining = call("GET", f"/references?keyword={TOKEN}") check("nothing of ours is left", remaining["total"] == 0, str(remaining["total"])) - check( - "and no labels either", - call("GET", "/reference-tags")["total"] == 0, - str(call("GET", "/reference-tags")["total"]), - ) + tags_left = call("GET", f"/reference-tags?keyword={TOKEN}") + check("and no labels either", tags_left["total"] == 0, str(tags_left["total"])) print(f"\nall {_checks} checks passed") return 0