Handle multiple numbers and add tests

create_biblio.py

@@ -213,14 +213,14 @@ def main():
     print("Updated: Finished")
 
 
-main()
-# file_path = "../test/Itineraries/Hulbert 1923 Some Medieval Advertisements of Rome.pdf"
-# doc = fitz.open(file_path)
-# page = doc[0]
-# print("page: ", page)
-# i, _ = getInfoFromFileName(file_path)
-# print("file-name-info: ", i)
-# info = getInfoGeneral(page)
-# print("infoLines: ", info)
-# output = parseInfoGeneral(info, i)
-# print("output: ", output)
+# main()
+file_path = "../test/Itineraries/Zurli 1998 Il cod Vindobonensis Palatinus 9401 asterisk dell Anthologia Latina.pdf"
+doc = fitz.open(file_path)
+page = doc[0]
+print("page: ", page)
+i, _ = getInfoFromFileName(file_path)
+print("file-name-info: ", i)
+info = getInfoGeneral(page)
+print("infoLines: ", info)
+output = parseInfoGeneral(info, i)
+print("output: ", output)

parse_info_functions.py

@@ -2,14 +2,39 @@
 import re
 import os
 
+
+def collectYearManuscriptCode(file_name, output):
+    space_sections = file_name.split(" ")
+    numbers4digits = re.findall(r"[0-9]{4}", file_name)
+    numbersAllDigits = re.findall(r"[0-9]{3,9}", file_name)
+    posYear = int(numbers4digits[0])
+    if (
+        numbers4digits
+        and len(numbers4digits) >= 1
+        and posYear > 0
+        and posYear < 2050
+        and space_sections[1] == numbers4digits[0]
+    ):
+        output["year"] = numbers4digits[0]
+        additionalNums = [x for x in numbersAllDigits if x != numbers4digits[0]]
+        if additionalNums:
+            output["number_of_volumes"] = additionalNums[0]
+    else:
+        output["number_of_volumes"] = numbersAllDigits[0]
+    return output
+
+
 # Has tests
 def getInfoFromFileName(file_path):
     print("Update: Collecting info from file name")
     output = {}
     file_name = os.path.basename(os.path.normpath(file_path))
     # Remove .pdf
     file_name = file_name.split(".")[0]
-    # Split on year
+
+    # Numbers
+    output = collectYearManuscriptCode(file_name, output)
+
     textSections = re.split(r"(?<!\d)\d{4}(?!\d)", file_name)
     if len(textSections) == 2 and textSections[1]:
         author, title = textSections
@@ -21,6 +46,7 @@ def getInfoFromFileName(file_path):
     elif len(textSections) == 2:
         title = textSections[0]
         output["title"] = title.strip()
+        print("Update: Article title found")
     elif len(textSections) > 2:
         author = textSections[0]
         title = textSections[1]
@@ -33,11 +59,6 @@ def getInfoFromFileName(file_path):
         output["title"] = file_name.strip()
         print("Update: Article title found")
 
-    year = re.findall(r"[0-9]{4}", file_name)
-    if len(year) >= 1:
-        output["year"] = year[0]
-        print("Update: Year published found")
-
     return output, 2
 
 

tests/test_parse_info_functions.py

@@ -4,11 +4,33 @@
 from parse_info_functions import (
     getInfoFromFileName,
     parseInfoGeneral,
-    findInfoJSTOR,
+    collectYearManuscriptCode,
 )
 
 fake = Faker()
 
+# collectYearManuscriptCode
+@pytest.mark.parametrize(
+    "file_name,output,expected",
+    [
+        (
+            "Ammannati 2023 Lupus in fabula - Sulla vera mano di Lupo di Ferrières",
+            {},
+            {"year": "2023"},
+        ),
+        (
+            "Zurli 1998 Il cod Vindobonensis Palatinus 9401 asterisk dell Anthologia Latina",
+            {},
+            {"year": "1998", "number_of_volumes": 9401},
+        ),
+        ("Levitan-DancingEndRope-1985", {}, {"year": 1985}),  # fails
+        ("Les manuscrits de Loup de Ferrières", {}, {}),  # fails
+    ],
+)
+def test_collectYearManuscriptCode(file_name, output, expected):
+    assert collectYearManuscriptCode(file_name, output) == expected
+
+
 # getInfoFromFileName
 def test_author_year_title_format():
     assert getInfoFromFileName(
@@ -37,7 +59,7 @@ def test_dashes():
     )
 
 
-def test_multiple_years_format():
+def test_multiple_numbers_format():
     assert getInfoFromFileName(
         "Zurli 1998 Il cod Vindobonensis Palatinus 9401 asterisk dell Anthologia Latina"
     ) == (
@@ -89,7 +111,11 @@ def test_no_year():
     {"authors": ["Zurli"], "title": "Il cod Vindobonensis Palatinus", "year": "1998"},
     infolines_middlebury_all_caps_expected,
 )
-infolines_jstor = []
+infolines_jstor = [
+    "Some Medieval Advertisements of Rome ",
+    "Author(s): J. R. Hulbert ",
+    "Source: Modern Philology , May, 1923, Vol. 20, No. 4 (May, 1923), pp. 403-424  Published by: The University of Chicago Press Stable URL: https://www.jstor.org/stable/433697JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of content in a trusted digital archive. We use information technology and tools to increase productivity and facilitate new forms of scholarship. For more information about JSTOR, please contact [email protected].  Your use of the JSTOR archive indicates your acceptance of the Terms & Conditions of Use, available at ",
+]
 no_infolines = ([], {"title": "blah, blah, blah"}, {"title": "blah, blah, blah"})
 # Persee - not working
 # infolines_persee_output = {'authors': ['Pellegrin'], 'title': 'Les manuscrits de Loup de Ferrières', 'year': '1957'}
@@ -133,8 +159,8 @@ def test_findInfoJSTOR(tmp_path):
     f1.parent.mkdir()  # create a directory "mydir" in temp folder (which is the parent directory of "myfile"
     f1.touch()  # create a file "myfile" in "mydir"
     # JSTOR_no_title = ((fitz.open('mydir/myfile')[0], ({'title': 'myfile'}, 2)))
-    doc = fitz.open("mydir/myfile.pdf")
-    assert findInfoJSTOR(doc[0], "mydir/myfile.pdf") == ({"title": "myfile"}, 2)
+    # doc = fitz.open("mydir/myfile.pdf")
+    # assert findInfoJSTOR(doc[0], "mydir/myfile.pdf") == ({"title": "myfile"}, 2)
 
 
 # Mock tools:
@@ -163,3 +189,10 @@ def test_findInfoJSTOR(tmp_path):
 # fake = Faker()
 
 # pip install Faker
+
+# Might be more for backend objects:
+# https://factoryboy.readthedocs.io/en/stable/
+
+# tmp_dir:  https://stackoverflow.com/questions/36070031/creating-a-temporary-directory-in-pytest
+# fitz open - https://github.com/pymupdf/PyMuPDF/issues/612
+# mocking issues - https://stackoverflow.com/questions/65728499/python-pytest-mocking-three-functions