Add testcase for bad file format

Author: khemarato

_quick_build.yml

@@ -21,11 +21,10 @@ exclude:
     - _authors/deleanu-f.md
     - _authors/diamond-jared.md
     - _authors/gomtsul.md
+    - _authors/gleig-a.md
     - _authors/huxley-a.md
     - _authors/iwamura-jane.md
-    - _authors/khema.md
     - _authors/lew-karl.md
-    - _authors/norman.md
     - _authors/rankine-claudia.md
     - _authors/shi-zhiru.md
     - _authors/sontag.md
@@ -41,9 +40,9 @@ exclude:
     - _authors/keeler-ward.md
     - _authors/king-winston.md
     - _authors/menzel-peter.md
-    - _authors/mipham.md
     - _authors/popova.md
     - _authors/singer-peter.md
+    - _authors/vasubandhu.md
     - _content/articles/astrological-determinism_kotyk-j.md
     - _content/articles/beginnings-of-the-buddhas-teachings-according-to-the-ea_bareau-andre.md
     - _content/articles/bill-gates-tweeted_matthews-dylan.md
@@ -363,4 +362,35 @@ exclude:
     - _content/reference/pressing-out-pure-honey_rogell-sharda.md
     - _content/reference/ticivara.md
     - _content/reference/tipitaka.md
+    - _content/articles/sa-regarding-emptiness_lamotte.md
+    - _content/av/buddhism-beyond-modernity_gleig-a.md
+    - _content/av/fear-and-worry_pasanno.md
+    - _content/av/feminism_solnit.md
+    - _content/av/fifty-jataka_baker-phongpaichit.md
+    - _content/av/great-indoors.md
+    - _content/av/literature-of-gandhara_salomon-richard.md
+    - _content/av/moral-panics_cottom-klein.md
+    - _content/av/muslim-stereotypes-conceal-the-real-history_elverskog-johan.md
+    - _content/av/tornado-of-self_panyavaddho.md
+    - _content/av/values_jayasaro.md
+    - _content/av/yasodhara_sasson-v.md
+    - _content/booklets/single-bowl-of-sauce_buddhadasa.md
+    - _content/canon/an6.45.md
+    - _content/canon/karma-vibhanga.md
+    - _content/canon/mn25.md
+    - _content/canon/mv1-4.md
+    - _content/canon/sn36.19.md
+    - _content/canon/t1586.md
+    - _content/essays/chan-practice-and-faith_sheng-yen.md
+    - _content/essays/cushion-or-world_cintita.md
+    - _content/essays/monet-refuses-the-operation_mueller-lisel.md
+    - _content/monographs/buddhist-thought_williams-paul.md
+    - _content/monographs/early-buddhist-transmission_neelis-jason.md
+    - _content/monographs/li-bo-unkempt_smith-kidder.md
+    - _content/articles/omniscience_analayo.md
+    - _content/av/secret-identity_tal.md
+    - _content/essays/ashokas-engineers_dhammika.md
+    - _content/excerpts/samadhi_analayo.md
+    - _content/excerpts/sati_analayo.md
+
 

_tests/content.md

@@ -10,6 +10,7 @@ A series of tests checking the integrity of the _content data
 | Count     | {% if site.content.size > 100 %}Pass ✅{% else %}FAIL ❌{% endif %}  | With {{ site.content.size }} items in the library. |
 | Excessive Authors | {% assign ea = site.content | where_exp: "c", "c.authors.size > 5" %}{% if ea.size == 0 %}Pass ✅{% else %}FAIL ❌{% endif %}  |  {% assign cout = '' | split: '' %}{% for c in ea %}{% assign cout = cout | push: c.path %}{% endfor %}Found {{ ea.size }} works with more than 5 authors{% if ea.size > 0 %}:{% else %}.{% endif %} {{ cout | array_to_sentence_string }}
 | Sane file_links | {% assign valid_buckets = "exclusive_01" | split: "," %}{% assign hostedcontent = site.content | where_exp: "c", "c.file_links.size > 0" %}{% assign fs = '' | split: '' %}{% for c in hostedcontent %}{% for l in c.file_links %}{% assign s = l | split: "/" %}{% unless valid_buckets contains s[0] %}{% assign fs = fs | push: c %}{% endunless %}{% endfor %}{% endfor %}{% if fs.size == 0 %}Pass ✅{% else %}FAIL ❌{% endif %}  |  {% assign count = hostedcontent.size | minus: fs.size %}{% if count > 0 %}There are {{ count }} sane links{% endif %}{% if fs.size > 0 %}The {{ fs.size }} pieces with bad buckets are: {% for c in fs %}[{{ c.title | split: ":" | first }}]({{ c.url }}) {% endfor %}{% endif %}
+| file_links match formats | {% assign fs = '' | split: '' %}{% for c in hostedcontent %}{% for l in c.file_links %}{% assign ee = l | split: "." | last %}{% unless ee == c.formats[forloop.index0] %}{% assign fs = fs | push: c %}{% endunless %}{% endfor %}{% endfor %}{% if fs.size == 0 %}Pass ✅{% else %}FAIL ❌{% endif %}  |  {% assign count = hostedcontent.size | minus: fs.size %}{% if count > 0 %}There are {{ count }} sane formats.{% endif %}{% if fs.size > 0 %} The {{ fs.size }} pieces with bad formats are: {% for c in fs %}[{{ c.title | split: ":" | first }}]({{ c.url }}) {% endfor %}{% endif %}
 | Missing Authors | {% assign expect = '' | split: '' %}{% for cont in site.content %}{% for auth in cont.authors %}{% unless auth contains " " %}{% unless expect contains auth %}{% assign expect = expect | push: auth %}{% endunless %}{% endunless %}{% endfor %}{% endfor %}{% assign grouped = expect | group_by_exp: "auth", "site.authors | where: 'slug', auth | size" %}{% for group in grouped %}{% if group.name == 0 %}{% assign failed = group.items %}{% else %}{% assign found = group.items %}{% endif %}{% endfor %}{% if expect.size == found.size %}Pass ✅{% else %}FAIL ❌{% endif %}  |  Of the {{ expect.size }} authors cited, {{ found.size }} of them are in the database. {% if failed.size > 0 %}Failed to find author pages for: {{ failed | array_to_sentence_string }}{% endif %}
 | Dangling Authors | {% assign authors = site.authors | map: "slug" %}{% for auth in found %}{% assign authors = authors | where_exp: "a", "a != auth" %}{% endfor %}{% assign unfound = '' | split: '' %}{% for auth in authors %}{% assign c = site.content | where: "translator", auth | size %}{% if c > 0 %}{% continue %}{% endif %}{% assign c = site.content | where: "editor", auth | size %}{% if c > 0 %}{% continue %}{% endif %}{% assign c = site.content | where: "reader", auth | size %}{% if c == 0 %}{% assign unfound = unfound | push: auth %}{% endif %}{% endfor %}{% if unfound.size == 0 %}Pass ✅{% else %}FAIL ❌{% endif %}  |  There are {{ unfound.size }} authors with no works attributed to them{% if unfound.size == 0 %}.{% else %}: {{ unfound | array_to_sentence_string }}.{% endif %}
 | Non-monograph content missing links | {% assign failures = site.content | where_exp: "c", "c.external_url == nil" | where_exp: "c", "c.drive_links == nil" | where_exp: "c", "c.source_url == nil" | where_exp: "c", "c.file_links == nil" | where_exp: "c", "c.category != 'monographs'" | where_exp: "c", "c.slug != 'baraka_fricke-ron'" | where_exp: "c", "c.slug != 'harvey'" %}{% if failures.size == 0 %}Pass ✅{% else %}FAIL ❌{% endif %} | Except for [_Baraka_](/content/av/baraka_fricke-ron) and [_Harvey_](/content/av/harvey) (known exceptions), there were {{ failures.size }} found{% if failures.size >0 %}: {{ failures | map: "slug" | array_to_sentence_string }}{% endif %}.