test: Fix formatting and annotation tests

papis_extract/formatter.py

@@ -10,8 +10,8 @@ def format_markdown(
 ) -> str:
     template = (
         "{{#tag}}#{{tag}}\n{{/tag}}"
-        "{{#quote}}> {{quote}}{{/quote}} {{#page}}[p. {{page}}]{{/page}}"
+        "{{#quote}}> {{quote}}{{/quote}}{{#page}} [p. {{page}}]{{/page}}"
-        "\n{{#note}}  NOTE: {{note}}{{/note}}"
+        "{{#note}}\n  NOTE: {{note}}{{/note}}"
     )
     output = ""
     for entry in docs:
@@ -30,11 +30,11 @@ def format_markdown(
 
         for a in entry.annotations:
             output += a.format(template)
-            output += "\n"
+            output += "\n\n"
 
         output += "\n\n\n"
 
-    return output
+    return output.rstrip()
 
 
 def format_markdown_atx(docs: list[AnnotatedDocument] = []) -> str:
@@ -63,7 +63,7 @@ def format_count(docs: list[AnnotatedDocument] = []) -> str:
             f"{count}\n"
         )
 
-    return output
+    return output.rstrip()
 
 
 def format_csv(docs: list[AnnotatedDocument] = []) -> str:
@@ -82,7 +82,7 @@ def format_csv(docs: list[AnnotatedDocument] = []) -> str:
             output += a.format(template, doc=d)
             output += "\n"
 
-    return output
+    return output.rstrip()
 
 
 formatters: dict[str, Formatter] = {

tests/test_annotation.py

@@ -1,25 +1,23 @@
+from papis.document import Document
 import pytest
-from papis_extract.annotation_data import Annotation
+from papis_extract.annotation import Annotation
-from papis_extract.templating import Custom
 
 
 @pytest.mark.parametrize(
     "fmt_string,expected",
     [
-        (Custom(string="{{quote}}"), "I am the text value"),
+        ("{{quote}}", "I am the text value"),
         (
-            Custom(string="> {{quote}}\n{{#note}}Note: {{note}}{{/note}}"),
+            "> {{quote}}\n{{#note}}Note: {{note}}{{/note}}",
             "> I am the text value\nNote: Whereas I represent the note",
         ),
         (
-            Custom(
+            "{{#note}}Note: {{note}}{{/note}}{{#page}}, p. {{page}}{{/page}}",
-                string="{{#note}}Note: {{note}}{{/note}}{{#page}}, p. {{page}}{{/page}}"
-            ),
             "Note: Whereas I represent the note",
         ),
     ],
 )
-def test_formatting(fmt_string, expected):
+def test_formatting_replacements(fmt_string, expected):
     sut = Annotation(
         "myfile",
         text="I am the text value",
@@ -28,6 +26,23 @@ def test_formatting(fmt_string, expected):
 
     assert sut.format(fmt_string) == expected
 
+@pytest.mark.parametrize(
+    "fmt_string,expected",
+    [
+        ("{{doc.title}}", "document-title"),
+        ("{{doc.title}}-{{doc.author}}", "document-title-document-author"),
+        ("{{quote}} ({{doc.author}})", "I am the text value (document-author)"),
+    ]
+)
+def test_formatting_document_access(fmt_string, expected):
+    sut = Annotation(
+        "myfile",
+        text="I am the text value",
+        content="Whereas I represent the note",
+    )
+    doc = Document(data= {"title": "document-title", "author": "document-author"})
+
+    assert sut.format(fmt_string, doc=doc) == expected
 
 def test_colorname_matches_exact():
     sut = Annotation("testfile", colors=(1.0, 0.0, 0.0), minimum_similarity_color=1.0)

tests/test_formatting.py

@@ -1,49 +1,59 @@
-import chevron
+from papis.document import Document
+from papis_extract.annotation import AnnotatedDocument, Annotation
 
-from papis_extract.templating import Markdown, Csv
+from papis_extract.formatter import (
+    format_count,
+    format_csv,
+    format_markdown,
+    format_markdown_atx,
+)
 
-
+an_doc: AnnotatedDocument = AnnotatedDocument(
-def test_template_markers():
+    Document(data={"author": "document-author", "title": "document-title"}),
-    ...
+    [
+        Annotation("myfile.pdf", text="my lovely text"),
+        Annotation("myfile.pdf", text="my second text", content="with note"),
+    ],
+)
 
 
 def test_markdown_default():
-    fmt = Markdown()
+    fmt = format_markdown
-    assert (
+    assert fmt([an_doc]) == (
-        chevron.render(
+        """==============   ---------------
-            fmt.string,
+document-title - document-author
-            {
+==============   ---------------
-                "file": "somefile/somewhere.pdf",
+
-                "quote": "I am quote",
+> my lovely text
-                "note": "and including note.",
+
-                "page": 46,
+> my second text
-                "tag": "important",
+  NOTE: with note"""
-                "type": "highlight",
-            },
-        )
-        == "#important\n> I am quote [p. 46]\n  NOTE: and including note."
     )
 
 
-def test_csv_string():
+def test_markdown_atx():
-    fmt = Csv()
+    fmt = format_markdown_atx
-    assert (
+    assert fmt([an_doc]) == (
-        chevron.render(
+        """# document-title - document-author
-            fmt.string,
+
-            {
+> my lovely text
-                "file": "somefile/somewhere.pdf",
+
-                "quote": "I am quote",
+> my second text
-                "note": "and including note.",
+  NOTE: with note"""
-                "page": 46,
-                "tag": "important",
-                "type": "highlight",
-            },
-        )
-        == "highlight, important, 46, "
-        "I am quote, and including note., somefile/somewhere.pdf"
     )
 
 
-def test_csv_header():
+def test_count_default():
-    fmt = Csv()
+    fmt = format_count
-    assert chevron.render(fmt.header, {}) == "type, tag, page, quote, note, file"
+    assert fmt([an_doc]) == ("""document-author - document-title: 2""")
+
+
+def test_csv_default():
+    fmt = format_csv
+    assert fmt([an_doc]) == (
+        "type,tag,page,quote,note,author,title,ref,file\n"
+        'Highlight,,0,"my lovely text","","document-author",'
+        '"document-title","","myfile.pdf"\n'
+        'Highlight,,0,"my second text","with note","document-author",'
+        '"document-title","","myfile.pdf"'
+    )