From df80836adaa126094f329f040f3049122efd1d1c Mon Sep 17 00:00:00 2001
From: hudssntao <hudsontao@gmail.com>
Date: Wed, 1 Nov 2023 01:35:24 -0400
Subject: [PATCH 1/5] Added pre-commit files with black, tested run commands
 which reformatted several files

---
 .github/workflows/pre-commit.yml | 17 +++++++++++++++++
 .pre-commit-config.yaml          |  5 +++++
 2 files changed, 22 insertions(+)
 create mode 100644 .github/workflows/pre-commit.yml
 create mode 100644 .pre-commit-config.yaml

diff --git a/.github/workflows/pre-commit.yml b/.github/workflows/pre-commit.yml
new file mode 100644
index 0000000..6e852cb
--- /dev/null
+++ b/.github/workflows/pre-commit.yml
@@ -0,0 +1,17 @@
+name: pre-commit
+on:
+  pull_request:
+  push:
+    branches: main
+permissions:
+  contents: read
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: "3.9"
+      - run: pip install pre-commit -r requirements.txt
+      - run: pre-commit run --all-files
\ No newline at end of file
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
new file mode 100644
index 0000000..7ac9b1e
--- /dev/null
+++ b/.pre-commit-config.yaml
@@ -0,0 +1,5 @@
+repos:
+-   repo: https://github.com/psf/black
+    rev: 23.10.1
+    hooks:
+    -   id: black
\ No newline at end of file

From c9f54ed260c72f01f6891c31f280f31eda623d9e Mon Sep 17 00:00:00 2001
From: Hudson Tao <hudsontao@gmail.com>
Date: Wed, 1 Nov 2023 12:22:35 -0400
Subject: [PATCH 2/5] Formatted files with black.

---
 setup.py                                      |  2 +-
 .../PKG-INFO                                  | 23 +++++++++++++++++++
 .../SOURCES.txt                               | 22 ++++++++++++++++++
 .../dependency_links.txt                      |  1 +
 src/prompt_systematic_review/keywords.py      | 20 ++++++++--------
 src/prompt_systematic_review/utils.py         |  8 +++----
 tests/test_utils.py                           |  8 ++++---
 7 files changed, 66 insertions(+), 18 deletions(-)
 create mode 100644 src/prompt_systematic_review.egg-info/PKG-INFO
 create mode 100644 src/prompt_systematic_review.egg-info/SOURCES.txt
 create mode 100644 src/prompt_systematic_review.egg-info/dependency_links.txt

diff --git a/setup.py b/setup.py
index fc1f76c..6068493 100644
--- a/setup.py
+++ b/setup.py
@@ -1,3 +1,3 @@
 from setuptools import setup
 
-setup()
\ No newline at end of file
+setup()
diff --git a/src/prompt_systematic_review.egg-info/PKG-INFO b/src/prompt_systematic_review.egg-info/PKG-INFO
new file mode 100644
index 0000000..2673bfd
--- /dev/null
+++ b/src/prompt_systematic_review.egg-info/PKG-INFO
@@ -0,0 +1,23 @@
+Metadata-Version: 2.1
+Name: prompt-systematic-review
+Version: 0.1.0
+Summary: a systematic review of prompting
+Home-page: https://github.com/trigaten/Prompt_Systematic_Review/
+Author: trigaten
+Author-email: sanderschulhoff@gmail.com
+License: MIT
+Classifier: Development Status :: 1 - Planning
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Science/Research
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Description-Content-Type: text/markdown
+License-File: LICENSE.txt
+
+# Prompt Engineering Survey
+
+## blacklist.csv
+
+Papers we should not include due to being poorly written or AI generated
diff --git a/src/prompt_systematic_review.egg-info/SOURCES.txt b/src/prompt_systematic_review.egg-info/SOURCES.txt
new file mode 100644
index 0000000..1c3493f
--- /dev/null
+++ b/src/prompt_systematic_review.egg-info/SOURCES.txt
@@ -0,0 +1,22 @@
+LICENSE.txt
+MANIFEST.in
+README.md
+setup.cfg
+setup.py
+examples/search_pe_papers.ipynb
+src/prompt_systematic_review/__init__.py
+src/prompt_systematic_review/keywords.py
+src/prompt_systematic_review/utils.py
+src/prompt_systematic_review.egg-info/PKG-INFO
+src/prompt_systematic_review.egg-info/SOURCES.txt
+src/prompt_systematic_review.egg-info/dependency_links.txt
+src/prompt_systematic_review.egg-info/requires.txt
+src/prompt_systematic_review.egg-info/top_level.txt
+src/prompt_systematic_review/__pycache__/__init__.cpython-311.pyc
+src/prompt_systematic_review/__pycache__/pipeline.cpython-311.pyc
+src/prompt_systematic_review/__pycache__/utils.cpython-311.pyc
+tests/__init__.py
+tests/test_utils.py
+tests/__pycache__/__init__.cpython-311.pyc
+tests/__pycache__/test_pipeline.cpython-311-pytest-7.4.0.pyc
+tests/__pycache__/test_utils.cpython-311-pytest-7.4.0.pyc
\ No newline at end of file
diff --git a/src/prompt_systematic_review.egg-info/dependency_links.txt b/src/prompt_systematic_review.egg-info/dependency_links.txt
new file mode 100644
index 0000000..8b13789
--- /dev/null
+++ b/src/prompt_systematic_review.egg-info/dependency_links.txt
@@ -0,0 +1 @@
+
diff --git a/src/prompt_systematic_review/keywords.py b/src/prompt_systematic_review/keywords.py
index b5d62aa..54b336e 100644
--- a/src/prompt_systematic_review/keywords.py
+++ b/src/prompt_systematic_review/keywords.py
@@ -1,11 +1,11 @@
 keywords_list = [
-        ["injection"],
-        ["gpt-3", "gpt 3"],
-        ["gpt-4", "gpt 4"],
-        ["prompt engineering"],
-        ["few shot", "few-shot"],
-        ["prompting"],
-        ["davinci", "text-davinci"],
-        ["chatgpt", "chat gpt", "gpt"],
-        ["generative ai", "generative artificial intelligence"]
-    ]
\ No newline at end of file
+    ["injection"],
+    ["gpt-3", "gpt 3"],
+    ["gpt-4", "gpt 4"],
+    ["prompt engineering"],
+    ["few shot", "few-shot"],
+    ["prompting"],
+    ["davinci", "text-davinci"],
+    ["chatgpt", "chat gpt", "gpt"],
+    ["generative ai", "generative artificial intelligence"],
+]
diff --git a/src/prompt_systematic_review/utils.py b/src/prompt_systematic_review/utils.py
index 3057002..5b82a11 100644
--- a/src/prompt_systematic_review/utils.py
+++ b/src/prompt_systematic_review/utils.py
@@ -1,14 +1,14 @@
 import requests
 from xml.etree import ElementTree as ET
 
-def search_arxiv(keyword,max_results=10000):
+
+def search_arxiv(keyword, max_results=10000):
     url = f"http://export.arxiv.org/api/query?search_query=all:{keyword}&start=0&max_results={max_results}"
     data = requests.get(url).content
     return data
 
+
 def count_articles(data):
     root = ET.fromstring(data)
-    entries = root.findall('{http://www.w3.org/2005/Atom}entry')
+    entries = root.findall("{http://www.w3.org/2005/Atom}entry")
     return len(entries)
-
-
diff --git a/tests/test_utils.py b/tests/test_utils.py
index 5195fd3..1d93dc2 100644
--- a/tests/test_utils.py
+++ b/tests/test_utils.py
@@ -2,10 +2,12 @@
 import pytest
 from prompt_systematic_review.utils import search_arxiv, count_articles
 
+
 def test_search_arxiv():
-    data = search_arxiv("covid",max_results=10)
+    data = search_arxiv("covid", max_results=10)
     assert len(data) > 0
 
+
 def test_count_articles():
-    data = search_arxiv("covid",max_results=10)
-    assert count_articles(data) == 10
\ No newline at end of file
+    data = search_arxiv("covid", max_results=10)
+    assert count_articles(data) == 10

From 645b9ef332a9896174585bc7f0e598c0677592ff Mon Sep 17 00:00:00 2001
From: hudssntao <145732608+hudssntao@users.noreply.github.com>
Date: Wed, 1 Nov 2023 13:56:08 -0400
Subject: [PATCH 3/5] Delete src/prompt_systematic_review.egg-info directory

---
 .../PKG-INFO                                  | 23 -------------------
 .../SOURCES.txt                               | 22 ------------------
 .../dependency_links.txt                      |  1 -
 3 files changed, 46 deletions(-)
 delete mode 100644 src/prompt_systematic_review.egg-info/PKG-INFO
 delete mode 100644 src/prompt_systematic_review.egg-info/SOURCES.txt
 delete mode 100644 src/prompt_systematic_review.egg-info/dependency_links.txt

diff --git a/src/prompt_systematic_review.egg-info/PKG-INFO b/src/prompt_systematic_review.egg-info/PKG-INFO
deleted file mode 100644
index 2673bfd..0000000
--- a/src/prompt_systematic_review.egg-info/PKG-INFO
+++ /dev/null
@@ -1,23 +0,0 @@
-Metadata-Version: 2.1
-Name: prompt-systematic-review
-Version: 0.1.0
-Summary: a systematic review of prompting
-Home-page: https://github.com/trigaten/Prompt_Systematic_Review/
-Author: trigaten
-Author-email: sanderschulhoff@gmail.com
-License: MIT
-Classifier: Development Status :: 1 - Planning
-Classifier: Environment :: Console
-Classifier: Intended Audience :: Science/Research
-Classifier: Natural Language :: English
-Classifier: Programming Language :: Python :: 3
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Description-Content-Type: text/markdown
-License-File: LICENSE.txt
-
-# Prompt Engineering Survey
-
-## blacklist.csv
-
-Papers we should not include due to being poorly written or AI generated
diff --git a/src/prompt_systematic_review.egg-info/SOURCES.txt b/src/prompt_systematic_review.egg-info/SOURCES.txt
deleted file mode 100644
index 1c3493f..0000000
--- a/src/prompt_systematic_review.egg-info/SOURCES.txt
+++ /dev/null
@@ -1,22 +0,0 @@
-LICENSE.txt
-MANIFEST.in
-README.md
-setup.cfg
-setup.py
-examples/search_pe_papers.ipynb
-src/prompt_systematic_review/__init__.py
-src/prompt_systematic_review/keywords.py
-src/prompt_systematic_review/utils.py
-src/prompt_systematic_review.egg-info/PKG-INFO
-src/prompt_systematic_review.egg-info/SOURCES.txt
-src/prompt_systematic_review.egg-info/dependency_links.txt
-src/prompt_systematic_review.egg-info/requires.txt
-src/prompt_systematic_review.egg-info/top_level.txt
-src/prompt_systematic_review/__pycache__/__init__.cpython-311.pyc
-src/prompt_systematic_review/__pycache__/pipeline.cpython-311.pyc
-src/prompt_systematic_review/__pycache__/utils.cpython-311.pyc
-tests/__init__.py
-tests/test_utils.py
-tests/__pycache__/__init__.cpython-311.pyc
-tests/__pycache__/test_pipeline.cpython-311-pytest-7.4.0.pyc
-tests/__pycache__/test_utils.cpython-311-pytest-7.4.0.pyc
\ No newline at end of file
diff --git a/src/prompt_systematic_review.egg-info/dependency_links.txt b/src/prompt_systematic_review.egg-info/dependency_links.txt
deleted file mode 100644
index 8b13789..0000000
--- a/src/prompt_systematic_review.egg-info/dependency_links.txt
+++ /dev/null
@@ -1 +0,0 @@
-

From f589722e0acd512d80bac04ee5dc39fdfc7c6f5c Mon Sep 17 00:00:00 2001
From: Hudson Tao <hudsontao@gmail.com>
Date: Wed, 1 Nov 2023 14:30:19 -0400
Subject: [PATCH 4/5] formatted paperSource.py and test_paper.py

---
 src/prompt_systematic_review/paperSource.py | 52 +++++++++++++++++++++
 tests/test_paper.py                         | 30 ++++++++++++
 2 files changed, 82 insertions(+)
 create mode 100644 src/prompt_systematic_review/paperSource.py
 create mode 100644 tests/test_paper.py

diff --git a/src/prompt_systematic_review/paperSource.py b/src/prompt_systematic_review/paperSource.py
new file mode 100644
index 0000000..ab7100b
--- /dev/null
+++ b/src/prompt_systematic_review/paperSource.py
@@ -0,0 +1,52 @@
+from abc import ABC, abstractmethod
+from typing import List, Tuple, Dict, Any
+from datetime import date
+from prompt_systematic_review import keywords
+import jellyfish as j
+
+
+class Paper:
+    def __init__(
+        self,
+        title: str,
+        firstAuthor: str,
+        url: str,
+        dateSubmitted: date,
+        keyWords: List[str],
+    ):
+        self.title = title
+        self.firstAuthor = firstAuthor
+        self.url = url
+        self.dateSubmitted = dateSubmitted
+        self.keywords = keyWords
+        try:
+            assert set(keyWords) == set([k.lower() for k in keyWords])
+        except:
+            raise ValueError("Keywords must be lowercase")
+
+    def __str__(self):
+        return f"{self.title}, by {self.firstAuthor}".strip()
+
+    def __eq__(self, other):
+        # this is to handle papers from different sources being the same
+        return (
+            j.jaro_winkler_similarity(self.__str__().lower(), other.__str__().lower())
+            > 0.75
+        )
+
+    def matchingKeyWords(self):
+        return [
+            keyword for keyword in keywords.keywords_list if keyword in self.keywords
+        ]
+
+
+class PaperSource(ABC):
+    baseURL: str
+
+    @abstractmethod
+    def getPapers(self, count: int, keyWords: List[str]) -> List[Paper]:
+        pass
+
+    @abstractmethod
+    def getPaperSrc(self, paper: Paper) -> str:
+        pass
diff --git a/tests/test_paper.py b/tests/test_paper.py
new file mode 100644
index 0000000..4764961
--- /dev/null
+++ b/tests/test_paper.py
@@ -0,0 +1,30 @@
+import pytest
+from prompt_systematic_review.paperSource import Paper
+from datetime import date
+
+
+def test_paper():
+    paper1 = Paper(
+        "How to write a paper",
+        "Harry Parnasus",
+        "example.com",
+        date(2000, 2, 2),
+        ["keyword1", "keyword2"],
+    )
+    paper2 = Paper(
+        "How to NOT write a paper",
+        "John Dickenson",
+        "example.com",
+        date(2002, 3, 3),
+        ["keyword1", "keyword2"],
+    )
+    alsoPaper1 = Paper(
+        "How to write a paper",
+        "Dr. Harry Parnasus",
+        "https://example2.com",
+        date(2000, 2, 5),
+        ["keyword1", "keyword2"],
+    )
+
+    assert paper1 == alsoPaper1
+    assert paper1 != paper2 and paper2 != alsoPaper1

From a139841271cd70083c5d6592250eb2bd27568d75 Mon Sep 17 00:00:00 2001
From: hudssntao <145732608+hudssntao@users.noreply.github.com>
Date: Wed, 1 Nov 2023 14:41:16 -0400
Subject: [PATCH 5/5] Update test_paper.py

---
 tests/test_paper.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/test_paper.py b/tests/test_paper.py
index 448572a..4764961 100644
--- a/tests/test_paper.py
+++ b/tests/test_paper.py
@@ -27,4 +27,4 @@ def test_paper():
     )
 
     assert paper1 == alsoPaper1
-    assert paper1 != paper2 and paper2 != alsoPaper1
\ No newline at end of file
+    assert paper1 != paper2 and paper2 != alsoPaper1