refactor dummy generation

7 files changed, 152 insertions, 163 deletions

diff --git a/fatcat/__init__.py b/fatcat/__init__.py
index d8494a19..b3a82a0f 100644
--- a/fatcat/__init__.py
+++ b/fatcat/__init__.py
@@ -7,27 +7,4 @@ app = Flask(__name__)
 app.config.from_object(Config)
 db = SQLAlchemy(app)
 
-examples = {
-    "work": {
-        "id": "rzga5b9cd7efgh04iljk",
-        "rev": "12345",
-        "redirect_id": None,
-        "edit_id": None,
-        "extra_json": None,
-        "title": "Structure and Interpretation",
-        "work_type": "journal-article",
-        "contributors": [
-            {"name": "Alyssa P. Hacker"},
-        ],
-        "primary": {
-            "title": "Structure and Interpretation",
-            "release_type": "online",
-            "date": "2000-01-01",
-            "doi": "10.491/599.sdo14",
-        },
-        "releases": [
-        ],
-    },
-}
-
-from fatcat import routes, models, api, sql
+from fatcat import routes, models, api, sql, dummy
diff --git a/fatcat/api.py b/fatcat/api.py
index c62d14a2..175d4d82 100644
--- a/fatcat/api.py
+++ b/fatcat/api.py
@@ -1,7 +1,7 @@
 
 from flask import Flask, render_template, send_from_directory, request, \
     url_for, abort, g, redirect, jsonify
-from fatcat import app, db, examples
+from fatcat import app, db
 from fatcat.models import *
 from fatcat.sql import *
 
diff --git a/fatcat/dummy.py b/fatcat/dummy.py
new file mode 100644
index 00000000..b547cf16
--- /dev/null
+++ b/fatcat/dummy.py
@@ -0,0 +1,135 @@
+
+import random
+import hashlib
+from fatcat import db
+from fatcat.models import *
+
+def insert_example_works():
+    """
+    TODO: doesn't create an edit trail (yet)
+    """
+
+    n_elkies = CreatorRev(
+        name="Noam D. Elkies",
+        sortname="Elkies, N",
+        orcid=None)
+    n_elkies_id = CreatorIdent(revision=n_elkies)
+    pi_work = WorkRev(
+        title="Why is π^2 so close to 10?",
+        work_type="journal-article")
+    pi_work_id = WorkIdent(revision=pi_work)
+    pi_release = ReleaseRev(
+        title=pi_work.title,
+        work_ident_id=pi_work.id,
+        release_type="journal-article")
+    pi_contrib = ReleaseContrib(creator=n_elkies_id)
+    pi_release.creators.append(pi_contrib)
+    pi_release_id = ReleaseIdent(revision=pi_release)
+    pi_work.primary_release = pi_release
+
+    # TODO:
+    #pi_file = File(
+    #    sha1="efee52e46c86691e2b892dbeb212f3b92e92e9d3",
+    #    url="http://www.math.harvard.edu/~elkies/Misc/pi10.pdf")
+    db.session.add_all([n_elkies, n_elkies_id, pi_work, pi_work_id, pi_release,
+        pi_release_id])
+
+    # TODO:
+    #ligo_collab = CreatorRev(name="LIGO Scientific Collaboration")
+    #ligo_paper = ReleaseRev(
+    #    title="Full Band All-sky Search for Periodic Gravitational Waves in the O1 LIGO Data")
+    db.session.commit()
+
+
+def insert_random_works(count=100):
+    """
+    TODO: doesn't create an edit trail (yet)
+    """
+
+    first_names = ("Sarah", "Robin", "Halko", "Jefferson", "Max", "桃井",
+        "Koizumi", "Rex", "Billie", "Tenzin")
+    last_names = ("Headroom", "はるこ", "Jun'ichirō", "Wong", "Smith")
+
+    author_revs = []
+    author_ids = []
+    for _ in range(count):
+        first = random.choice(first_names)
+        last = random.choice(last_names)
+        ar = CreatorRev(
+            name="{} {}".format(first, last),
+            sortname="{}, {}".format(last, first[0]),
+            orcid=None)
+        author_revs.append(ar)
+        author_ids.append(CreatorIdent(revision=ar))
+
+    container_revs = []
+    container_ids = []
+    for _ in range(5):
+        cr = ContainerRev(
+            name="The Fake Journal of Stuff",
+            #container_id=None,
+            publisher="Big Paper",
+            sortname="Fake Journal of Stuff",
+            issn="1234-5678")
+        container_revs.append(cr)
+        container_ids.append(ContainerIdent(revision=cr))
+
+    title_start = ("All about ", "When I grow up I want to be",
+        "The final word on", "Infinity: ", "The end of")
+    title_ends = ("Humankind", "Bees", "Democracy", "Avocados", "«küßî»", "“ЌύБЇ”")
+    work_revs = []
+    work_ids = []
+    release_revs = []
+    release_ids = []
+    file_revs = []
+    file_ids = []
+    for _ in range(count):
+        title = "{} {}".format(random.choice(title_start), random.choice(title_ends))
+        work = WorkRev(title=title)
+        work_id = WorkIdent(revision=work)
+        authors = set(random.sample(author_ids, 5))
+        release = ReleaseRev(
+            title=work.title,
+            creators=[ReleaseContrib(creator=a) for a in list(authors)],
+            #work=work,
+            container=random.choice(container_ids))
+        release_id = ReleaseIdent(revision=release)
+        work.primary_release = release
+        authors.add(random.choice(author_ids))
+        release2 = ReleaseRev(
+            title=work.title + " (again)",
+            creators=[ReleaseContrib(creator=a) for a in list(authors)],
+            #work=work,
+            container=random.choice(container_ids))
+        release_id2 = ReleaseIdent(revision=release2)
+        work_revs.append(work)
+        work_ids.append(work_id)
+        release_revs.append(release)
+        release_revs.append(release2)
+        release_ids.append(release_id)
+        release_ids.append(release_id2)
+
+        file_content = str(random.random()) * random.randint(3,100)
+        file_sha = hashlib.sha1(file_content.encode('utf-8')).hexdigest()
+        file_rev = FileRev(
+            sha1=file_sha,
+            size=len(file_content),
+            url="http://archive.invalid/{}".format(file_sha),
+            releases=[FileRelease(release=release_id), FileRelease(release=release_id2)],
+        )
+        file_id = FileIdent(revision=file_rev)
+        file_revs.append(file_rev)
+        file_ids.append(file_id)
+
+    db.session.add_all(author_revs)
+    db.session.add_all(author_ids)
+    db.session.add_all(work_revs)
+    db.session.add_all(work_ids)
+    db.session.add_all(release_revs)
+    db.session.add_all(release_ids)
+    db.session.add_all(container_revs)
+    db.session.add_all(container_ids)
+    db.session.add_all(file_revs)
+    db.session.add_all(file_ids)
+
+    db.session.commit()
diff --git a/fatcat/models.py b/fatcat/models.py
index 43e0bfea..ce7e2e13 100644
--- a/fatcat/models.py
+++ b/fatcat/models.py
@@ -225,15 +225,15 @@ class Editor(db.Model):
     username = db.Column(db.String)
     group = db.Column(db.String)
 
-
-### Other ###################################################################
-
 class ChangelogEntry(db.Model):
     __tablename__= 'changelog'
     id = db.Column(db.Integer, primary_key=True, autoincrement=True)
     edit_group_id = db.Column(db.ForeignKey('edit_group.id'))
     timestamp = db.Column(db.Integer)
 
+
+### Other ###################################################################
+
 class ExtraJson(db.Model):
     __tablename__ = 'extra_json'
     sha1 = db.Column(db.String, primary_key=True)
diff --git a/fatcat/routes.py b/fatcat/routes.py
index c59922b3..3c1822ce 100644
--- a/fatcat/routes.py
+++ b/fatcat/routes.py
@@ -2,7 +2,7 @@
 import os
 from flask import Flask, render_template, send_from_directory, request, \
     url_for, abort, g, redirect, jsonify
-from fatcat import app, db, examples
+from fatcat import app, db
 
 
 ### Views ###################################################################
@@ -13,7 +13,7 @@ def work_create():
 
 @app.route('/work/random', methods=['GET'])
 def work_random():
-    work = examples['work']
+    work = {} # XXX
     return render_template('work_view.html', work=work, primary=work['primary'])
 
 @app.route('/work/random', methods=['GET'])
diff --git a/fatcat/sql.py b/fatcat/sql.py
index 45980925..c38e6f0e 100644
--- a/fatcat/sql.py
+++ b/fatcat/sql.py
@@ -6,134 +6,7 @@ from fatcat import db
 from fatcat.models import *
 
 def populate_db():
-    """
-    TODO: doesn't create an edit trail (yet)
-    """
-
-    n_elkies = CreatorRev(
-        name="Noam D. Elkies",
-        sortname="Elkies, N",
-        orcid=None)
-    n_elkies_id = CreatorIdent(revision=n_elkies)
-    pi_work = WorkRev(
-        title="Why is π^2 so close to 10?",
-        work_type="journal-article")
-    pi_work_id = WorkIdent(revision=pi_work)
-    pi_release = ReleaseRev(
-        title=pi_work.title,
-        work_ident_id=pi_work.id,
-        release_type="journal-article")
-    pi_contrib = ReleaseContrib(creator=n_elkies_id)
-    pi_release.creators.append(pi_contrib)
-    pi_release_id = ReleaseIdent(revision=pi_release)
-    pi_work.primary_release = pi_release
-
-    # TODO:
-    #pi_file = File(
-    #    sha1="efee52e46c86691e2b892dbeb212f3b92e92e9d3",
-    #    url="http://www.math.harvard.edu/~elkies/Misc/pi10.pdf")
-    db.session.add_all([n_elkies, n_elkies_id, pi_work, pi_work_id, pi_release,
-        pi_release_id])
-
-    # TODO:
-    #ligo_collab = CreatorRev(name="LIGO Scientific Collaboration")
-    #ligo_paper = ReleaseRev(
-    #    title="Full Band All-sky Search for Periodic Gravitational Waves in the O1 LIGO Data")
-    db.session.commit()
-
-
-def populate_complex_db(count=100):
-    """
-    TODO: doesn't create an edit trail (yet)
-    """
-
-    first_names = ("Sarah", "Robin", "Halko", "Jefferson", "Max", "桃井",
-        "Koizumi", "Rex", "Billie", "Tenzin")
-    last_names = ("Headroom", "はるこ", "Jun'ichirō", "Wong", "Smith")
-
-    author_revs = []
-    author_ids = []
-    for _ in range(count):
-        first = random.choice(first_names)
-        last = random.choice(last_names)
-        ar = CreatorRev(
-            name="{} {}".format(first, last),
-            sortname="{}, {}".format(last, first[0]),
-            orcid=None)
-        author_revs.append(ar)
-        author_ids.append(CreatorIdent(revision=ar))
-
-    container_revs = []
-    container_ids = []
-    for _ in range(5):
-        cr = ContainerRev(
-            name="The Fake Journal of Stuff",
-            #container_id=None,
-            publisher="Big Paper",
-            sortname="Fake Journal of Stuff",
-            issn="1234-5678")
-        container_revs.append(cr)
-        container_ids.append(ContainerIdent(revision=cr))
-
-    title_start = ("All about ", "When I grow up I want to be",
-        "The final word on", "Infinity: ", "The end of")
-    title_ends = ("Humankind", "Bees", "Democracy", "Avocados", "«küßî»", "“ЌύБЇ”")
-    work_revs = []
-    work_ids = []
-    release_revs = []
-    release_ids = []
-    file_revs = []
-    file_ids = []
-    for _ in range(count):
-        title = "{} {}".format(random.choice(title_start), random.choice(title_ends))
-        work = WorkRev(title=title)
-        work_id = WorkIdent(revision=work)
-        authors = set(random.sample(author_ids, 5))
-        release = ReleaseRev(
-            title=work.title,
-            creators=[ReleaseContrib(creator=a) for a in list(authors)],
-            #work=work,
-            container=random.choice(container_ids))
-        release_id = ReleaseIdent(revision=release)
-        work.primary_release = release
-        authors.add(random.choice(author_ids))
-        release2 = ReleaseRev(
-            title=work.title + " (again)",
-            creators=[ReleaseContrib(creator=a) for a in list(authors)],
-            #work=work,
-            container=random.choice(container_ids))
-        release_id2 = ReleaseIdent(revision=release2)
-        work_revs.append(work)
-        work_ids.append(work_id)
-        release_revs.append(release)
-        release_revs.append(release2)
-        release_ids.append(release_id)
-        release_ids.append(release_id2)
-
-        file_content = str(random.random()) * random.randint(3,100)
-        file_sha = hashlib.sha1(file_content.encode('utf-8')).hexdigest()
-        file_rev = FileRev(
-            sha1=file_sha,
-            size=len(file_content),
-            url="http://archive.invalid/{}".format(file_sha),
-            releases=[FileRelease(release=release_id), FileRelease(release=release_id2)],
-        )
-        file_id = FileIdent(revision=file_rev)
-        file_revs.append(file_rev)
-        file_ids.append(file_id)
-
-    db.session.add_all(author_revs)
-    db.session.add_all(author_ids)
-    db.session.add_all(work_revs)
-    db.session.add_all(work_ids)
-    db.session.add_all(release_revs)
-    db.session.add_all(release_ids)
-    db.session.add_all(container_revs)
-    db.session.add_all(container_ids)
-    db.session.add_all(file_revs)
-    db.session.add_all(file_ids)
-
-    db.session.commit()
+    pass
 
 def add_crossref(meta):
 
diff --git a/tests/test_backend.py b/tests/test_backend.py
index 93e3f11a..7a139ef7 100644
--- a/tests/test_backend.py
+++ b/tests/test_backend.py
@@ -28,6 +28,7 @@ class FatcatTestCase(unittest.TestCase):
         fatcat.db.session.remove()
         fatcat.db.drop_all()
         fatcat.db.create_all()
+        fatcat.sql.populate_db()
 
     def test_health(self):
         rv = self.app.get('/health')
@@ -35,7 +36,7 @@ class FatcatTestCase(unittest.TestCase):
         assert obj['ok']
 
     def test_works(self):
-        fatcat.sql.populate_db()
+        fatcat.dummy.insert_example_works()
 
         # Invalid Id
         rv = self.app.get('/v0/work/_')
@@ -61,8 +62,11 @@ class FatcatTestCase(unittest.TestCase):
     def test_populate(self):
         fatcat.sql.populate_db()
 
-    def test_populate_complex(self):
-        fatcat.sql.populate_complex_db()
+    def test_example_works(self):
+        fatcat.dummy.insert_example_works()
+
+    def test_random_works(self):
+        fatcat.dummy.insert_random_works()
 
     def test_load_crossref(self):
         with open('./tests/files/crossref-works.2018-01-21.badsample.json', 'r') as f:
@@ -71,9 +75,9 @@ class FatcatTestCase(unittest.TestCase):
             fatcat.sql.add_crossref(obj)
 
     def test_hydrate_work(self):
-        fatcat.sql.populate_complex_db()
+        fatcat.dummy.insert_random_works()
         fatcat.sql.hydrate_work(1)
 
     def test_hydrate_release(self):
-        fatcat.sql.populate_complex_db()
+        fatcat.dummy.insert_random_works()
         fatcat.sql.hydrate_release(1)