Migrate code from pecha.org api

.github/workflows/CI.yml

@@ -16,20 +16,20 @@ jobs:
 
     steps:
     - uses: actions/checkout@v3
-    
+
     - name: Set up Python 3.8
       uses: actions/setup-python@v3
       with:
         python-version: "3.8"
-        
+
     - name: Install dependencies
       run: |
         pip install -U pip
         pip install .
         pip install .[dev]
-        
+
     - name: Test with pytest
       run: PYTHONPATH=src pytest
-    
+
     - name: Test Coverage
-      run: PYTHONPATH=src pytest --cov project_name
+      run: PYTHONPATH=src pytest --cov pecha_uploader

.pre-commit-config.yaml

@@ -31,11 +31,6 @@ repos:
         args: ["--config=setup.cfg"]
         additional_dependencies: [flake8-isort]
 
-  - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.982
-    hooks:
-      - id: mypy
-        additional_dependencies: [types-all]
 
 # sets up .pre-commit-ci.yaml to ensure pre-commit dependencies stay up to date
 ci:

README.md

@@ -9,14 +9,12 @@
 </h1>
 
 ## _Project Name_
-_The project name should match its code's capability so that new users can easily understand what it does._
+_Pecha Uploader_
 
 ## Owner(s)
 
 _Change to the owner(s) of the new repo. (This template's owners are:)_
-- [@ngawangtrinley](https://github.com/ngawangtrinley)
-- [@mikkokotila](https://github.com/mikkokotila)
-- [@evanyerburgh](https://github.com/evanyerburgh)
+- [@sandup](https://github.com/lobsam)
 
 
 ## Table of contents
@@ -56,16 +54,16 @@ Get started with _Project Name_ by _(write the first step a user needs to start
 
 
 ### Install _Project Name_
-1. _Write the step here._ 
+1. _Write the step here._
+
+    _Explanatory text here_
 
-    _Explanatory text here_ 
-
     _(Optional: Include a code sample or screenshot that helps your users complete this step.)_
 
 2. _Write the step here._
- 
-    a. _Substep 1_ 
-    
+
+    a. _Substep 1_
+
     b. _Substep 2_
 
 

pyproject.toml

@@ -3,12 +3,12 @@ requires = ["setuptools>=61.0"]
 build-backend = "setuptools.build_meta"
 
 [project]
-name = "project_name"
+name = "pecha_uploader"
 version = "0.0.1"
 authors = [
   { name="OpenPecha", email="dev@openpecha.org" },
 ]
-description = "A small example package"
+description = "This project handles the pecha api in order to upload text/pecha to pecha.org"
 readme = "README.md"
 requires-python = ">=3.8"
 classifiers = [

requirements.txt

@@ -0,0 +1 @@
+jsonpickle

src/pecha_uploader/category/extract.py

@@ -0,0 +1,27 @@
+import urllib
+from urllib.error import HTTPError
+
+from pecha_uploader.config import baseURL, headers
+
+
+def get_category(category_name: str):
+    """
+    Check full category path for variable `category_name`.
+        `category_name`: str, example: "Indian Treatises/Madyamika/The way of the bodhisattvas"
+    """
+    url = baseURL + "api/category/" + urllib.parse.quote(category_name)
+    req = urllib.request.Request(url, method="GET", headers=headers)
+
+    try:
+        response = urllib.request.urlopen(req)
+        res = response.read().decode("utf-8")
+        print(res)
+        if "error" not in res:
+            return {"status": True}
+        elif "already exists" in res["error"]:
+            return {"status": True}
+        return {"status": False, "error": res}
+    except HTTPError as e:
+        print("[categories] Error code: ", e.code)
+        print(e.read())
+        return {"status": False, "error": res}

src/pecha_uploader/category/upload.py

@@ -0,0 +1,46 @@
+import json
+from typing import List
+from urllib.error import HTTPError
+from urllib.parse import urlencode
+from urllib.request import Request, urlopen
+
+from pecha_uploader.config import PECHA_API_KEY, baseURL, headers
+
+
+def post_category(en_category_list: List[str], bo_category_list: List[str]):
+    """
+    Post path for article categorizing.
+    You MUST use post_term() before using post_category().
+        `pathLIST`: list of str,
+    if you want to post path = "Indian Treatises/Madyamika/The way of the bodhisattvas"
+        => post_category(["Indian Treatises"])
+        => post_category(["Indian Treatises", "Madyamika"])
+        => post_category(["Indian Treatises", "Madyamika", "The way of the bodhisattvas"])
+    """
+    url = baseURL + "api/category"
+    category = {
+        "sharedTitle": list(map(lambda x: x["name"], en_category_list))[-1],
+        "path": list(map(lambda x: x["name"], en_category_list)),
+        "enDesc": list(map(lambda x: x["enDesc"], en_category_list))[-1],
+        "heDesc": list(map(lambda x: x["heDesc"], bo_category_list))[-1],
+        "enShortDesc": list(map(lambda x: x["enShortDesc"], en_category_list))[-1],
+        "heShortDesc": list(map(lambda x: x["heShortDesc"], bo_category_list))[-1],
+    }
+    input_json = json.dumps(category)
+    values = {"json": input_json, "apikey": PECHA_API_KEY}
+
+    data = urlencode(values)
+    binary_data = data.encode("ascii")
+    req = Request(url, binary_data, headers=headers)
+
+    try:
+        response = urlopen(req)
+        res = response.read().decode("utf-8")
+        if "error" not in res:
+            return {"status": True}
+        elif "already exists" in res:
+            return {"status": True}
+        return {"status": True, "error": res}
+    except HTTPError as e:
+        print("Error code: ", e, list(map(lambda x: x["name"], en_category_list))[-1])
+        return {"status": False, "error": e}

src/pecha_uploader/config.py

@@ -0,0 +1,13 @@
+import os
+
+PECHA_API_KEY = os.getenv("PECHA_API_KEY")
+if not PECHA_API_KEY:
+    raise ValueError("Please set PECHA_API_KEY environment variable")
+
+headers = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"  # noqa
+}
+BASEPATH = os.path.dirname(os.path.abspath(__file__))  # path to `Pecha.org/tools`
+
+# baseURL = "https://staging.pecha.org/"
+baseURL = "http://127.0.0.1:8000/"

src/pecha_uploader/index/extract.py

@@ -0,0 +1,22 @@
+import json
+import urllib
+from urllib.error import HTTPError
+
+from pecha_uploader.config import baseURL, headers
+
+
+def get_index(index: str):
+    """
+    Get Index information for article name `index`.
+        `index`: str, article en name
+    """
+    index_url = baseURL + "api/v2/raw/index"
+    prepare_index_str = index.replace(" ", "_")
+    url = f"{index_url}/{prepare_index_str}?with_content_counts=1"
+    req = urllib.request.Request(url, method="GET", headers=headers)
+    try:
+        response = urllib.request.urlopen(req)
+        print(json.loads(response.read().decode("utf-8")))
+    except HTTPError as e:
+        print("Error code: ", e.code)
+        print(e.read().decode("utf-8"))

src/pecha_uploader/index/upload.py

@@ -0,0 +1,62 @@
+import json
+import urllib
+from typing import Dict, List
+from urllib.error import HTTPError
+
+from pecha_uploader.config import PECHA_API_KEY, baseURL, headers
+
+
+def post_index(index_str: str, category_list: List[str], nodes: Dict):
+    """ "
+    Post index value for article settings.
+        `index`: str, article title,
+        `catLIST`: list of str, category list (see post_category() for example),
+        `titleLIST`: list of json, title name in different language,
+            titleLIST = {
+                "lang": "en/he",
+                "text": "Your en/he title",
+                "primary": True (You must have a primary title for each language)
+            }
+    """
+    url = (
+        baseURL + "api/v2/raw/index/" + urllib.parse.quote(index_str.replace(" ", "_"))
+    )
+
+    # "titles" : titleLIST,
+    # "key" : index,
+    # "nodeType" : "JaggedArrayNode",
+    # # "lengths" : [4, 50],
+    # "depth" : 2,
+    # "sections" : ["Chapter", "Verse"],
+    # "addressTypes" : ["Integer", "Integer"],
+
+    index = {"title": "", "categories": [], "schema": {}}
+    index["title"] = index_str
+    index["categories"] = list(map(lambda x: x["name"], category_list))
+    index["schema"] = nodes
+
+    # if text is commentary
+    if "base_text_mapping" in category_list[-1].keys():
+        index["base_text_titles"] = category_list[-1]["base_text_titles"]
+        index["base_text_mapping"] = category_list[-1]["base_text_mapping"]
+        index["collective_title"] = index_str
+        index["dependence"] = category_list[-1]["link"]
+
+    input_json = json.dumps(index, indent=4, ensure_ascii=False)
+
+    values = {
+        "json": input_json,
+        "apikey": PECHA_API_KEY,
+    }
+    data = urllib.parse.urlencode(values)
+    binary_data = data.encode("ascii")
+    req = urllib.request.Request(url, binary_data, headers=headers)
+    try:
+        response = urllib.request.urlopen(req)
+        res = response.read().decode("utf-8")
+        if "error" in res and "already exists." not in res:
+            return {"status": False, "error": res}
+        return {"status": True}
+    except HTTPError as e:
+        print("Error code: ", e.code, e.read())
+        return {"status": False, "error": e.read()}