From 57d1dc7b9bc50238eeaac4f9c6a0b0d1c80cdc4b Mon Sep 17 00:00:00 2001
From: Yi Ge <me@yige.ch>
Date: Sat, 20 Apr 2019 23:21:41 +0200
Subject: [PATCH] add initial models

---
 .gitignore          | 125 ++++++++++++++++++++++++++++++++++++++++++++
 Pipfile             |  14 +++++
 Pipfile.lock        | 121 ++++++++++++++++++++++++++++++++++++++++++
 videocr/__init__.py |   0
 videocr/models.py   |  47 +++++++++++++++++
 5 files changed, 307 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 Pipfile
 create mode 100644 Pipfile.lock
 create mode 100644 videocr/__init__.py
 create mode 100644 videocr/models.py

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..e8b0168
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,125 @@
+.DS_Store
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don’t work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
diff --git a/Pipfile b/Pipfile
new file mode 100644
index 0000000..e4e1418
--- /dev/null
+++ b/Pipfile
@@ -0,0 +1,14 @@
+[[source]]
+name = "pypi"
+url = "https://pypi.org/simple"
+verify_ssl = true
+
+[dev-packages]
+
+[packages]
+pytesseract = "*"
+pillow = "*"
+opencv-python = "*"
+
+[requires]
+python_version = "3.7"
diff --git a/Pipfile.lock b/Pipfile.lock
new file mode 100644
index 0000000..035c89b
--- /dev/null
+++ b/Pipfile.lock
@@ -0,0 +1,121 @@
+{
+    "_meta": {
+        "hash": {
+            "sha256": "101aa7956bfaa0af4aa5a78b93d953f90855c84fb51aac77ba22f1b4facea2d3"
+        },
+        "pipfile-spec": 6,
+        "requires": {
+            "python_version": "3.7"
+        },
+        "sources": [
+            {
+                "name": "pypi",
+                "url": "https://pypi.org/simple",
+                "verify_ssl": true
+            }
+        ]
+    },
+    "default": {
+        "numpy": {
+            "hashes": [
+                "sha256:1980f8d84548d74921685f68096911585fee393975f53797614b34d4f409b6da",
+                "sha256:22752cd809272671b273bb86df0f505f505a12368a3a5fc0aa811c7ece4dfd5c",
+                "sha256:23cc40313036cffd5d1873ef3ce2e949bdee0646c5d6f375bf7ee4f368db2511",
+                "sha256:2b0b118ff547fecabc247a2668f48f48b3b1f7d63676ebc5be7352a5fd9e85a5",
+                "sha256:3a0bd1edf64f6a911427b608a894111f9fcdb25284f724016f34a84c9a3a6ea9",
+                "sha256:3f25f6c7b0d000017e5ac55977a3999b0b1a74491eacb3c1aa716f0e01f6dcd1",
+                "sha256:4061c79ac2230594a7419151028e808239450e676c39e58302ad296232e3c2e8",
+                "sha256:560ceaa24f971ab37dede7ba030fc5d8fa173305d94365f814d9523ffd5d5916",
+                "sha256:62be044cd58da2a947b7e7b2252a10b42920df9520fc3d39f5c4c70d5460b8ba",
+                "sha256:6c692e3879dde0b67a9dc78f9bfb6f61c666b4562fd8619632d7043fb5b691b0",
+                "sha256:6f65e37b5a331df950ef6ff03bd4136b3c0bbcf44d4b8e99135d68a537711b5a",
+                "sha256:7a78cc4ddb253a55971115f8320a7ce28fd23a065fc33166d601f51760eecfa9",
+                "sha256:80a41edf64a3626e729a62df7dd278474fc1726836552b67a8c6396fd7e86760",
+                "sha256:893f4d75255f25a7b8516feb5766c6b63c54780323b9bd4bc51cdd7efc943c73",
+                "sha256:972ea92f9c1b54cc1c1a3d8508e326c0114aaf0f34996772a30f3f52b73b942f",
+                "sha256:9f1d4865436f794accdabadc57a8395bd3faa755449b4f65b88b7df65ae05f89",
+                "sha256:9f4cd7832b35e736b739be03b55875706c8c3e5fe334a06210f1a61e5c2c8ca5",
+                "sha256:adab43bf657488300d3aeeb8030d7f024fcc86e3a9b8848741ea2ea903e56610",
+                "sha256:bd2834d496ba9b1bdda3a6cf3de4dc0d4a0e7be306335940402ec95132ad063d",
+                "sha256:d20c0360940f30003a23c0adae2fe50a0a04f3e48dc05c298493b51fd6280197",
+                "sha256:d3b3ed87061d2314ff3659bb73896e622252da52558f2380f12c421fbdee3d89",
+                "sha256:dc235bf29a406dfda5790d01b998a1c01d7d37f449128c0b1b7d1c89a84fae8b",
+                "sha256:fb3c83554f39f48f3fa3123b9c24aecf681b1c289f9334f8215c1d3c8e2f6e5b"
+            ],
+            "version": "==1.16.2"
+        },
+        "opencv-python": {
+            "hashes": [
+                "sha256:1703a296a96d3d46615e5053f224867977accb4240bcaa0fcabcb0768bf5ac13",
+                "sha256:1777ce7535ee7a1995cae168a107a1320e9df13648b930e72a1a2c2eccd64cda",
+                "sha256:1e5520482fb18fbd64d079e7f17ac0018f195fd75f6360a53bb82d7903106b50",
+                "sha256:25522dcf2529614750a71112a6659759080b4bdc2323f19d47f4d895960fd796",
+                "sha256:2af5f2842ad44c65ae2647377e0ff198719e1a1cfc9c6a19bc0c525c035d4bd8",
+                "sha256:31ec48d7eca13fc25c287dea7cecab453976e372cad8f50d55c054a247efda21",
+                "sha256:47cf48ff5dbd554e9f58cc9e98cf0b5de3f6a971172612bffa06bc5fb79ce872",
+                "sha256:494f98366bb5d6c2ac7e50e6617139f353704fd97a6d12ec9d392e72817d5cb0",
+                "sha256:4a9845870739e640e3350a8d98d511c92c087fe3d66090e83be7bf94e0ac64f7",
+                "sha256:4ac29cc0847d948a6636899014e84e165c30cc8779d6218394d44363462a01ce",
+                "sha256:5857ace03b7854221abf8072462d306c2c2ce4e366190b21d90ee8ee8aaf5bb4",
+                "sha256:5b4a23d99d5a2874767034466f5a8fd37b9f93ac14955a01b1a208983c76b9ad",
+                "sha256:734d87a5021c037064beb62133e135e66c7128e401a63b8b842b809ae2093749",
+                "sha256:78005c1c5d15ef4e32e0f485557bd15b5b6d87f49c19db7fe3e9246a61ebe7e4",
+                "sha256:81ae2283225c5c52fc3d72debd4241c30ccff2bb922578bf7867f9851cce3acb",
+                "sha256:88dbf900f297fdae0f62b899d6a784d8868ec2135854c5f8a9abbad00a6f0c5b",
+                "sha256:8c98ea7b8d327a31cd6028782a06147d0e0329ae8e829e881fb5d02f7ed8aec9",
+                "sha256:937d4686fef6967921145290f5b50c01c00c5b5d3542a6519e8a85cd88448723",
+                "sha256:a057958c0e362b3c4f03b9af1cbdb6d5af035fd22ecd7fd794eba8fdeb049eb8",
+                "sha256:c41eab31fa2c641226c6187caa391a688d064c99f078d604574f1912296b771f",
+                "sha256:cf4f7e62d1f80d1fa85a1693a3500def5cde54b2b75212b3609e552e4c25acfb",
+                "sha256:d90d60143e18334330c149f293071c9f2f3c79c896f33dc4ec65099e58baaaa7",
+                "sha256:db3106b7ca86999a7bd1f2fcc93e49314e5e6e451356774e421a69428df5020b",
+                "sha256:dbaf264db56f4771dfac6624f438bc4dc670aa94f61a6138848fcab7e9e77380",
+                "sha256:e65206c4cf651dc9cf0829962fae8bec986767c9f123d6a1ad17f9356bf7257e",
+                "sha256:eac94ddc78c58e891cff7180274317dad2938a4ddfc6ced1c04846c7f50e77e9",
+                "sha256:f2e828711f044a965509c862b3a59b3181e9c56c145a950cb53d43fec54e66d2"
+            ],
+            "index": "pypi",
+            "version": "==4.1.0.25"
+        },
+        "pillow": {
+            "hashes": [
+                "sha256:15c056bfa284c30a7f265a41ac4cbbc93bdbfc0dfe0613b9cb8a8581b51a9e55",
+                "sha256:1a4e06ba4f74494ea0c58c24de2bb752818e9d504474ec95b0aa94f6b0a7e479",
+                "sha256:1c3c707c76be43c9e99cb7e3d5f1bee1c8e5be8b8a2a5eeee665efbf8ddde91a",
+                "sha256:1fd0b290203e3b0882d9605d807b03c0f47e3440f97824586c173eca0aadd99d",
+                "sha256:24114e4a6e1870c5a24b1da8f60d0ba77a0b4027907860188ea82bd3508c80eb",
+                "sha256:258d886a49b6b058cd7abb0ab4b2b85ce78669a857398e83e8b8e28b317b5abb",
+                "sha256:33c79b6dd6bc7f65079ab9ca5bebffb5f5d1141c689c9c6a7855776d1b09b7e8",
+                "sha256:367385fc797b2c31564c427430c7a8630db1a00bd040555dfc1d5c52e39fcd72",
+                "sha256:3c1884ff078fb8bf5f63d7d86921838b82ed4a7d0c027add773c2f38b3168754",
+                "sha256:44e5240e8f4f8861d748f2a58b3f04daadab5e22bfec896bf5434745f788f33f",
+                "sha256:46aa988e15f3ea72dddd81afe3839437b755fffddb5e173886f11460be909dce",
+                "sha256:74d90d499c9c736d52dd6d9b7221af5665b9c04f1767e35f5dd8694324bd4601",
+                "sha256:809c0a2ce9032cbcd7b5313f71af4bdc5c8c771cb86eb7559afd954cab82ebb5",
+                "sha256:85d1ef2cdafd5507c4221d201aaf62fc9276f8b0f71bd3933363e62a33abc734",
+                "sha256:8c3889c7681af77ecfa4431cd42a2885d093ecb811e81fbe5e203abc07e0995b",
+                "sha256:9218d81b9fca98d2c47d35d688a0cea0c42fd473159dfd5612dcb0483c63e40b",
+                "sha256:9aa4f3827992288edd37c9df345783a69ef58bd20cc02e64b36e44bcd157bbf1",
+                "sha256:9d80f44137a70b6f84c750d11019a3419f409c944526a95219bea0ac31f4dd91",
+                "sha256:b7ebd36128a2fe93991293f997e44be9286503c7530ace6a55b938b20be288d8",
+                "sha256:c4c78e2c71c257c136cdd43869fd3d5e34fc2162dc22e4a5406b0ebe86958239",
+                "sha256:c6a842537f887be1fe115d8abb5daa9bc8cc124e455ff995830cc785624a97af",
+                "sha256:cf0a2e040fdf5a6d95f4c286c6ef1df6b36c218b528c8a9158ec2452a804b9b8",
+                "sha256:cfd28aad6fc61f7a5d4ee556a997dc6e5555d9381d1390c00ecaf984d57e4232",
+                "sha256:dca5660e25932771460d4688ccbb515677caaf8595f3f3240ec16c117deff89a",
+                "sha256:de7aedc85918c2f887886442e50f52c1b93545606317956d65f342bd81cb4fc3",
+                "sha256:e6c0bbf8e277b74196e3140c35f9a1ae3eafd818f7f2d3a15819c49135d6c062"
+            ],
+            "index": "pypi",
+            "version": "==6.0.0"
+        },
+        "pytesseract": {
+            "hashes": [
+                "sha256:11c20321595b6e2e904b594633edf1a717212b13bac7512986a2d807b8849770"
+            ],
+            "index": "pypi",
+            "version": "==0.2.6"
+        }
+    },
+    "develop": {}
+}
diff --git a/videocr/__init__.py b/videocr/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/videocr/models.py b/videocr/models.py
new file mode 100644
index 0000000..16c1137
--- /dev/null
+++ b/videocr/models.py
@@ -0,0 +1,47 @@
+from __future__ import annotations
+from typing import List
+from dataclasses import dataclass
+
+
+CONFIDENCE_THRESHOLD = 60
+# predictions with lower confidence will be filtered out
+
+
+@dataclass
+class PredictedWord:
+    __slots__ = 'confidence', 'text'
+    confidence: int
+    text: str
+
+
+class PredictedFrame:
+    words: List[PredictedWord]
+
+    def __init__(self, pred_data: str):
+        self.words = []
+
+        block_current = 1
+        for line in pred_data.split('\n')[1:]:
+            tmp = line.split()
+            if len(tmp) < 12:
+                # no word is predicted
+                continue
+            _, _, block_num, *_, conf, text = tmp
+            block_num, conf = int(block_num), int(conf)
+
+            # handle line breaks
+            if block_current < block_num:
+                block_current = block_num
+                self.words.append(PredictedWord(0, '\n'))
+
+            if conf >= CONFIDENCE_THRESHOLD:
+                self.words.append(PredictedWord(conf, text))
+
+    @property
+    def confidence(self) -> int:
+        return sum(word.confidence for word in self.words)
+
+    @property
+    def text(self) -> str:
+        return ''.join(word.text + ' ' for word in self.words)
+