Merge pull request #30 from chnm/stanza-import

Django management command for importing the stanzas

manuscript/admin.py

@@ -139,7 +139,6 @@ class SingleManuscriptAdmin(ImportExportModelAdmin):
     )
     search_fields = ("siglum",)
     resource_class = SingleManuscriptResource
-    readonly_fields = ("item_id",)
 
 
 class FolioAdmin(admin.ModelAdmin):
@@ -204,6 +203,14 @@ def save_related(self, request, form, formsets, change):
 
 class StanzaAdmin(admin.ModelAdmin):
     inlines = [StanzaVariantInline]
+    list_display = (
+        "stanza_line_code_starts",
+        "stanza_text",
+    )
+    search_fields = (
+        "stanza_text",
+        "stanza_line_code_starts",
+    )
 
 
 class StanzaVariantAdmin(admin.ModelAdmin):

manuscript/management/commands/load_stanzas.py

@@ -1,28 +1,66 @@
+import logging
+import re
+
 from django.core.management.base import BaseCommand
 
-from manuscript.models import Stanza
+from manuscript.models import SingleManuscript, Stanza
+
+logger = logging.getLogger(__name__)
 
 
 class Command(BaseCommand):
-    help = "Insert stanzas from a text file"
+    help = "Import poem data from a plain text file"
 
     def add_arguments(self, parser):
         parser.add_argument(
-            "file_path", type=str, help="The path to the file that contains the stanzas"
+            "--filepath", type=str, help="filepath of the plain text file to load"
+        )
+
+    def handle(self, *args, **options):
+        file_path = options.get("filepath")
+
+        with open(file_path, "r", encoding="utf-8-sig") as file:
+            content = file.read()
+
+        self.import_poem(content)
+
+    def import_poem(self, content):
+        manuscript = SingleManuscript.objects.get(siglum="TEST")
+        book_pattern = re.compile(r"^\s*LIBRO (\d+)", re.MULTILINE)
+        stanza_pattern = re.compile(
+            r"^(\d+)\.\s*(.*?)(?=\n\d+\.|\Z)", re.DOTALL | re.MULTILINE
         )
 
-    def handle(self, *args, **kwargs):
-        file_path = kwargs["file_path"]
-        with open(file_path, "r", encoding="utf-8") as file:
-            line_counter = 0
-            for line in file:
-                line = line.strip()
-                if line.startswith("[RUBRIC]") or line.isdigit():
-                    continue
-                if line != "":
-                    line_counter += 1
-                    line_number = f"01.02.{line_counter:02d}"
-                    stanza = Stanza(line=line, line_number=line_number)
-                    stanza.save()
-                else:
-                    line_counter = 0
+        book_matches = book_pattern.split(content)
+        if book_matches[0] == "":
+            book_matches = book_matches[1:]
+
+        for i in range(0, len(book_matches), 2):
+            book_number = int(
+                book_matches[i]
+            )  # Extract book number from "LIBRO X" string
+            book_text = book_matches[
+                i + 1
+            ].strip()  # Get the corresponding book content
+
+            stanza_matches = stanza_pattern.findall(book_text)
+
+            for stanza_number, stanza_text in stanza_matches:
+                stanza_number = int(stanza_number)
+                stanza_text = stanza_text.strip()
+
+                stanza_lines = stanza_text.split("\n")
+
+                for line_number, line_text in enumerate(stanza_lines, start=1):
+                    line_code = (
+                        f"{book_number:02d}.{stanza_number:02d}.{line_number:02d}"
+                    )
+                    # print(f"Line code: {line_code}, Line text: {line_text}")
+
+                    Stanza.objects.create(
+                        stanza_line_code_starts=line_code,
+                        stanza_text=line_text,
+                        related_manuscript=manuscript,
+                    )
+
+        self.stdout.write(self.style.SUCCESS("Successfully imported the stanzas"))

manuscript/migrations/0071_alter_folio_options_alter_stanza_options.py

@@ -0,0 +1,20 @@
+# Generated by Django 5.0.2 on 2024-05-30 16:43
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("manuscript", "0070_alter_location_line_code_alter_location_placename_id"),
+    ]
+
+    operations = [
+        migrations.AlterModelOptions(
+            name="folio",
+            options={"ordering": ["folio_number"]},
+        ),
+        migrations.AlterModelOptions(
+            name="stanza",
+            options={"ordering": ["id"]},
+        ),
+    ]

manuscript/models.py

@@ -5,6 +5,8 @@
 from django.conf import settings
 from django.core.exceptions import ValidationError
 from django.db import models
+from django.db.models import IntegerField
+from django.db.models.functions import Cast
 from django_prose_editor.fields import ProseEditorField
 from prose.fields import RichTextField
 
@@ -347,6 +349,9 @@ def derive_folio_location(self):
             manuscript=self.related_folio.manuscript, folio_number=book
         ).first()
 
+    class Meta:
+        ordering = ["id"]
+
 
 class Folio(models.Model):
     """This provides a way to collect several stanzas onto a single page, and associate them with a single manuscript."""

manuscript/views.py

@@ -3,6 +3,9 @@
 from django.urls import reverse
 from django.views import generic
 
+from manuscript.models import Stanza
+
 
 def index(request: HttpRequest):
-    return render(request, "index.html", {})
+    stanzas = Stanza.objects.all().order_by("stanza_line_code_starts")
+    return render(request, "index.html", {"stanzas": stanzas})

templates/index.html

@@ -4,4 +4,9 @@ <h2>Homepage</h2>
 
 {% block content %}
 
+    <h3>Text of the manuscript</h3>
+    {% for stanza in stanzas %}
+        <p>{{ stanza.stanza_text }}</p>
+    {% endfor %}
+
 {% endblock content %}