test: Additional unicode tests (moved)

about-code · Sep 26, 2019 · 45ebb23 · 45ebb23
1 parent ab6ec64
commit 45ebb23
Show file tree

Hide file tree

Showing 14 changed files with 427 additions and 207 deletions.
diff --git a/test/input/features/config-glossaries/glossarify-md.conf.json b/test/input/features/config-glossaries/glossarify-md.conf.json
@@ -10,7 +10,8 @@
         { "file": "./disjunct-terms-glossary-a.md", "termHint": " (a/b)"},
         { "file": "./disjunct-terms-glossary-b.md", "termHint": " (a/b)"},
         { "file": "./shared-terms-glossary-a.md", "termHint": " (a&b)"},
-        { "file": "./shared-terms-glossary-b.md", "termHint": " (a&b)"}
+        { "file": "./shared-terms-glossary-b.md", "termHint": " (a&b)"},
+        { "file": "./unicode-glossary.md", "termHint": ""}
     ],
     "linking": "relative",
     "ignoreCase": false,

diff --git a/test/input/features/config-glossaries/unicode-document.md b/test/input/features/config-glossaries/unicode-document.md
@@ -0,0 +1,46 @@
+<!-- =========== DE ============= -->
+
+GIVEN term 'äöüß Term begins with Umlauts'
+THEN the linker MUST link the term with its glossary definition.
+
+GIVEN term 'Term ends with Umlauts äöüß'
+THEN the linker MUST link the term with its glossary definition.
+
+GIVEN term 'Term contains äöüß Umlauts'
+THEN the linker MUST link the term with its glossary definition.
+
+GIVEN term 'Der Tod und das Mädchen'
+THEN the linker MUST link the term with its glossary definition.
+
+GIVEN term 'Äquator'
+THEN the linker MUST link the term with its glossary definition.
+
+GIVEN a compound term 'Äquatorregion' AND GIVEN 'Äquator' is a glossary term
+THEN the linker MUST NOT link the compound with a glossary definition.
+
+GIVEN a compound term 'Faßöl'
+WITH 'Faß' being a glossary term
+ AND 'Faß' ending with a non-ASCII character
+ AND 'öl' beginning with a non-ASCII character
+THEN 'Faßöl' MUST NOT be split into two words
+AND 'Faßöl' MUST NOT be linked to the glossary definition of 'Faß'.
+
+<!-- =========== ZH ============= -->
+
+GIVEN a term '中国' with non-ASCII chinese symbols
+THEN the linker MUST link the term with its glossary definition.
+
+GIVEN a term 'zhōngguó' with non-ASCII symbols
+THEN the linker MUST link the term with its glossary definition.
+
+GIVEN a term '中国China' beginning with non-ASCII chinese symbols
+THEN the linker MUST link the term with its glossary definition.
+
+GIVEN a term 'China中国' ending with non-ASCII chinese symbols
+THEN the linker MUST link the term with its glossary definition.
+
+GIVEN a term '中China国' beginning and ending with non-ASCII chinese symbols
+THEN the linker MUST link the term with its glossary definition.
+
+GIVEN a term 'Chi中国na' containing non-ASCII chinese symbols
+THEN the linker MUST link the term with its glossary definition.
diff --git a/test/input/features/config-glossaries/unicode-glossary.md b/test/input/features/config-glossaries/unicode-glossary.md
@@ -0,0 +1,54 @@
+# Unicode Tests
+
+<!-- =========== DE ============= -->
+
+## äöüß Term begins with Umlauts
+
+Testing German Umlauts.
+
+## Term ends with Umlauts äöüß
+
+Testing German Umlauts.
+
+## Term contains äöüß Umlauts
+
+Testing German Umlauts.
+
+## Der Tod und das Mädchen
+
+Classical composition by Franz Schubert (The Death and the Maiden).
+
+## Äquator
+
+GIVEN a compound term 'Äquatorregion' AND GIVEN 'Äquator' is a glossary term
+THEN the linker MUST NOT link the compound with a glossary definition.
+
+## Faß
+
+GIVEN a compound term 'Faßöl'
+WITH 'Faß' being a glossary term
+ AND 'Faß' ending with a non-ASCII character
+ AND 'öl' beginning with a non-ASCII character
+THEN 'Faßöl' MUST NOT be split into two words
+AND 'Faßöl' MUST NOT be linked to the glossary definition of 'Faß'.
+
+
+<!-- =========== ZH ============= -->
+
+## 中国
+China
+
+## zhōngguó
+China (spelling)
+
+## 中国China
+Word begins with symbols
+
+## China中国
+Word ends with symbols
+
+## 中China国
+Word begins and ends with symbols
+
+## Chi中国na
+Word contains symbols
diff --git a/test/input/features/i18n/document_de.md b/test/input/features/i18n/document_de.md
diff --git a/test/input/features/i18n/glossary_de.md b/test/input/features/i18n/glossary_de.md
diff --git a/test/input/glossarify-md.conf.json b/test/input/glossarify-md.conf.json
@@ -14,8 +14,7 @@
         { "file": "./glossary.md", "termHint": "↴"},
         { "file": "./glossary_formatted.md", "termHint": "ⓕ"},
         { "file": "./paths/uppercase/Glossary_Uppercase.md" },
-        { "file": "./features/aliases_and_synonyms/glossary.md" },
-        { "file": "./features/i18n/glossary_de.md"}
+        { "file": "./features/aliases_and_synonyms/glossary.md" }
     ],
     "linking": "relative",
     "ignoreCase": false,

diff --git a/test/output-expected/features/config-glossaries/glossarify-md.conf.json b/test/output-expected/features/config-glossaries/glossarify-md.conf.json
@@ -10,7 +10,8 @@
         { "file": "./disjunct-terms-glossary-a.md", "termHint": " (a/b)"},
         { "file": "./disjunct-terms-glossary-b.md", "termHint": " (a/b)"},
         { "file": "./shared-terms-glossary-a.md", "termHint": " (a&b)"},
-        { "file": "./shared-terms-glossary-b.md", "termHint": " (a&b)"}
+        { "file": "./shared-terms-glossary-b.md", "termHint": " (a&b)"},
+        { "file": "./unicode-glossary.md", "termHint": ""}
     ],
     "linking": "relative",
     "ignoreCase": false,

diff --git a/test/output-expected/features/config-glossaries/terms.json b/test/output-expected/features/config-glossaries/terms.json
@@ -1,4 +1,116 @@
 [
+  {
+    "shortDesc": "",
+    "term": "äöüß Term begins with Umlauts",
+    "hint": "",
+    "longDesc": "Testing German Umlauts.",
+    "anchor": "#äöüß-term-begins-with-umlauts",
+    "glossary": {
+      "file": "./unicode-glossary.md",
+      "termHint": "",
+      "basePath": "/{redacted}/input/features/config-glossaries/unicode-glossary.md",
+      "outPath": "/{redacted}/output-actual/features/config-glossaries/unicode-glossary.md"
+    },
+    "regex": {},
+    "aliases": [],
+    "ignoreCase": false
+  },
+  {
+    "shortDesc": "",
+    "term": "Äquator",
+    "hint": "",
+    "longDesc": "GIVEN a compound term 'Äquatorregion' AND GIVEN 'Äquator' is a glossary term\nTHEN the linker MUST NOT link the compound with a glossary definition.",
+    "anchor": "#äquator",
+    "glossary": {
+      "file": "./unicode-glossary.md",
+      "termHint": "",
+      "basePath": "/{redacted}/input/features/config-glossaries/unicode-glossary.md",
+      "outPath": "/{redacted}/output-actual/features/config-glossaries/unicode-glossary.md"
+    },
+    "regex": {},
+    "aliases": [],
+    "ignoreCase": false
+  },
+  {
+    "shortDesc": "",
+    "term": "China中国",
+    "hint": "",
+    "longDesc": "Word ends with symbols",
+    "anchor": "#china中国",
+    "glossary": {
+      "file": "./unicode-glossary.md",
+      "termHint": "",
+      "basePath": "/{redacted}/input/features/config-glossaries/unicode-glossary.md",
+      "outPath": "/{redacted}/output-actual/features/config-glossaries/unicode-glossary.md"
+    },
+    "regex": {},
+    "aliases": [],
+    "ignoreCase": false
+  },
+  {
+    "shortDesc": "",
+    "term": "Chi中国na",
+    "hint": "",
+    "longDesc": "Word contains symbols",
+    "anchor": "#chi中国na",
+    "glossary": {
+      "file": "./unicode-glossary.md",
+      "termHint": "",
+      "basePath": "/{redacted}/input/features/config-glossaries/unicode-glossary.md",
+      "outPath": "/{redacted}/output-actual/features/config-glossaries/unicode-glossary.md"
+    },
+    "regex": {},
+    "aliases": [],
+    "ignoreCase": false
+  },
+  {
+    "shortDesc": "",
+    "term": "Der Tod und das Mädchen",
+    "hint": "",
+    "longDesc": "Classical composition by Franz Schubert (The Death and the Maiden).",
+    "anchor": "#der-tod-und-das-mädchen",
+    "glossary": {
+      "file": "./unicode-glossary.md",
+      "termHint": "",
+      "basePath": "/{redacted}/input/features/config-glossaries/unicode-glossary.md",
+      "outPath": "/{redacted}/output-actual/features/config-glossaries/unicode-glossary.md"
+    },
+    "regex": {},
+    "aliases": [],
+    "ignoreCase": false
+  },
+  {
+    "shortDesc": "",
+    "term": "Faß",
+    "hint": "",
+    "longDesc": "GIVEN a compound term 'Faßöl'\nWITH 'Faß' being a glossary term AND 'Faß' ending with a non-ASCII character AND 'öl' beginning with a non-ASCII character\nTHEN 'Faßöl' MUST NOT be split into two words\nAND 'Faßöl' MUST NOT be linked to the glossary definition of 'Faß'.",
+    "anchor": "#faß",
+    "glossary": {
+      "file": "./unicode-glossary.md",
+      "termHint": "",
+      "basePath": "/{redacted}/input/features/config-glossaries/unicode-glossary.md",
+      "outPath": "/{redacted}/output-actual/features/config-glossaries/unicode-glossary.md"
+    },
+    "regex": {},
+    "aliases": [],
+    "ignoreCase": false
+  },
+  {
+    "shortDesc": "",
+    "term": "Term contains äöüß Umlauts",
+    "hint": "",
+    "longDesc": "Testing German Umlauts.",
+    "anchor": "#term-contains-äöüß-umlauts",
+    "glossary": {
+      "file": "./unicode-glossary.md",
+      "termHint": "",
+      "basePath": "/{redacted}/input/features/config-glossaries/unicode-glossary.md",
+      "outPath": "/{redacted}/output-actual/features/config-glossaries/unicode-glossary.md"
+    },
+    "regex": {},
+    "aliases": [],
+    "ignoreCase": false
+  },
   {
     "shortDesc": "",
     "term": "Term Disjunct A",
@@ -31,6 +143,22 @@
     "aliases": [],
     "ignoreCase": false
   },
+  {
+    "shortDesc": "",
+    "term": "Term ends with Umlauts äöüß",
+    "hint": "",
+    "longDesc": "Testing German Umlauts.",
+    "anchor": "#term-ends-with-umlauts-äöüß",
+    "glossary": {
+      "file": "./unicode-glossary.md",
+      "termHint": "",
+      "basePath": "/{redacted}/input/features/config-glossaries/unicode-glossary.md",
+      "outPath": "/{redacted}/output-actual/features/config-glossaries/unicode-glossary.md"
+    },
+    "regex": {},
+    "aliases": [],
+    "ignoreCase": false
+  },
   {
     "shortDesc": "",
     "term": "Term Shared A",
@@ -94,5 +222,69 @@
     "regex": {},
     "aliases": [],
     "ignoreCase": false
+  },
+  {
+    "shortDesc": "",
+    "term": "zhōngguó",
+    "hint": "",
+    "longDesc": "China (spelling)",
+    "anchor": "#zhōngguó",
+    "glossary": {
+      "file": "./unicode-glossary.md",
+      "termHint": "",
+      "basePath": "/{redacted}/input/features/config-glossaries/unicode-glossary.md",
+      "outPath": "/{redacted}/output-actual/features/config-glossaries/unicode-glossary.md"
+    },
+    "regex": {},
+    "aliases": [],
+    "ignoreCase": false
+  },
+  {
+    "shortDesc": "",
+    "term": "中China国",
+    "hint": "",
+    "longDesc": "Word begins and ends with symbols",
+    "anchor": "#中china国",
+    "glossary": {
+      "file": "./unicode-glossary.md",
+      "termHint": "",
+      "basePath": "/{redacted}/input/features/config-glossaries/unicode-glossary.md",
+      "outPath": "/{redacted}/output-actual/features/config-glossaries/unicode-glossary.md"
+    },
+    "regex": {},
+    "aliases": [],
+    "ignoreCase": false
+  },
+  {
+    "shortDesc": "",
+    "term": "中国",
+    "hint": "",
+    "longDesc": "China",
+    "anchor": "#中国",
+    "glossary": {
+      "file": "./unicode-glossary.md",
+      "termHint": "",
+      "basePath": "/{redacted}/input/features/config-glossaries/unicode-glossary.md",
+      "outPath": "/{redacted}/output-actual/features/config-glossaries/unicode-glossary.md"
+    },
+    "regex": {},
+    "aliases": [],
+    "ignoreCase": false
+  },
+  {
+    "shortDesc": "",
+    "term": "中国China",
+    "hint": "",
+    "longDesc": "Word begins with symbols",
+    "anchor": "#中国china",
+    "glossary": {
+      "file": "./unicode-glossary.md",
+      "termHint": "",
+      "basePath": "/{redacted}/input/features/config-glossaries/unicode-glossary.md",
+      "outPath": "/{redacted}/output-actual/features/config-glossaries/unicode-glossary.md"
+    },
+    "regex": {},
+    "aliases": [],
+    "ignoreCase": false
   }
 ]