From 2fba4a4de165ce854e2fb574043872f6535fddfa Mon Sep 17 00:00:00 2001 From: Chris Proctor Date: Wed, 15 Jan 2025 15:04:59 -0500 Subject: [PATCH] text codecs ready --- .gitignore | 3 + evaluate_codecs.py | 75 +++++++++++++++++++++++ poetry.lock | 118 +++++++++++++++++------------------- pyproject.toml | 6 +- text_codecs/alphanumeric.py | 39 ++++++++++++ text_codecs/ascii7.py | 33 ++++++++++ text_codecs/register.py | 17 ++++++ 7 files changed, 228 insertions(+), 63 deletions(-) create mode 100644 .gitignore create mode 100644 evaluate_codecs.py create mode 100644 text_codecs/alphanumeric.py create mode 100644 text_codecs/ascii7.py create mode 100644 text_codecs/register.py diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..eda5cd4 --- /dev/null +++ b/.gitignore @@ -0,0 +1,3 @@ +.DS_Store +__pycache__ +texts/* diff --git a/evaluate_codecs.py b/evaluate_codecs.py new file mode 100644 index 0000000..8aff393 --- /dev/null +++ b/evaluate_codecs.py @@ -0,0 +1,75 @@ +from argparse import ArgumentParser +from pathlib import Path +import codecs +import requests +from tabulate import tabulate +import sys +import shutil + +codecs_dir = "text_codecs" + +def evaluate_encoding(encoding, text_path): + "" + print(f"Evaluating encoding {encoding}") + try: + codecs.lookup(encoding) + except LookupError: + __import__(encoding) + text = Path(text_path).read_text() + compressed_path = Path(text_path).with_suffix('.' + encoding) + if compressed_path.exists(): + compressed = compressed_path.read_bytes() + else: + compressed = text.encode(encoding) + compressed_path.write_bytes(compressed) + original_size = len(text.encode('utf8')) + compressed_size = len(compressed) + return { + 'encoding': encoding, + 'original': original_size, + 'compressed': compressed_size, + 'compression_rate': compressed_size / original_size + } + +def inspect_encoded_text(encoding, text_path): + try: + codecs.lookup(encoding) + except LookupError: + __import__(encoding) + compressed_path = Path(text_path).with_suffix('.' + encoding) + if not compressed_path.exists(): + compressed = Path(text_path).read_text().encode(encoding) + compressed_path.write_bytes(compressed) + with open(compressed_path, 'rb') as fh: + text = fh.read().decode(encoding) + return text + +text_dir = Path("texts") +default_text = "texts/little_women.txt" +default_text_url = "https://www.gutenberg.org/cache/epub/37106/pg37106.txt" + +parser = ArgumentParser("A command-line tool which measures compression rates.") +parser.add_argument("encodings", nargs="*") +parser.add_argument("--inspect", "-i", help="See resulting text for a codec") +parser.add_argument("--text", "-t", default="texts/little_women.txt", help="Text file to use for testing") +parser.add_argument("--clean", "-c", action="store_true", help="Remove all generated files") +args = parser.parse_args() +if args.clean: + shutil.rmtree(text_dir) +if not text_dir.exists(): + text_dir.mkdir() +if not Path(args.text).exists(): + if args.text == default_text: + print("Downloading 'little_women.txt' from Project Gutenberg...") + response = requests.get(default_text_url, stream=True) + with open(default_text, 'wb') as f: + f.write(response.content) + else: + raise ValueError(f"{args.text} does not exist") +sys.path.append(codecs_dir) +if args.encodings: + results = [evaluate_encoding(e, args.text) for e in args.encodings] + print(tabulate(results, headers="keys")) +if args.inspect: + print(inspect_encoded_text(args.inspect, args.text)) + diff --git a/poetry.lock b/poetry.lock index 17816bc..764dbe1 100644 --- a/poetry.lock +++ b/poetry.lock @@ -263,14 +263,14 @@ files = [ [[package]] name = "easybits" -version = "0.1.3" +version = "0.1.4" description = "A friendly interface for exploring bits." optional = false python-versions = "<4.0,>=3.9" groups = ["main"] files = [ - {file = "easybits-0.1.3-py3-none-any.whl", hash = "sha256:3ed24ea1672eb29066d6fd8c61d8426d2bb153da15bbd37251ef1340b03f2566"}, - {file = "easybits-0.1.3.tar.gz", hash = "sha256:e854c64ca5418ffbf85e9b91eefc6b5d0fa210e7136b48453884ccde3b426483"}, + {file = "easybits-0.1.4-py3-none-any.whl", hash = "sha256:f0059ad99564717332dd52c1c6d417caa71195a288038268a2b93c62f5bc87f7"}, + {file = "easybits-0.1.4.tar.gz", hash = "sha256:2cae9c40098d9d27135c39beb1ad528409b9a744330dd30cacb8f6fd374fb9e7"}, ] [package.dependencies] @@ -339,67 +339,48 @@ files = [ [[package]] name = "numpy" -version = "2.2.1" +version = "1.26.4" description = "Fundamental package for array computing in Python" optional = false -python-versions = ">=3.10" +python-versions = ">=3.9" groups = ["main"] files = [ - {file = "numpy-2.2.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:5edb4e4caf751c1518e6a26a83501fda79bff41cc59dac48d70e6d65d4ec4440"}, - {file = "numpy-2.2.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:aa3017c40d513ccac9621a2364f939d39e550c542eb2a894b4c8da92b38896ab"}, - {file = "numpy-2.2.1-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:61048b4a49b1c93fe13426e04e04fdf5a03f456616f6e98c7576144677598675"}, - {file = "numpy-2.2.1-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:7671dc19c7019103ca44e8d94917eba8534c76133523ca8406822efdd19c9308"}, - {file = "numpy-2.2.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4250888bcb96617e00bfa28ac24850a83c9f3a16db471eca2ee1f1714df0f957"}, - {file = "numpy-2.2.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a7746f235c47abc72b102d3bce9977714c2444bdfaea7888d241b4c4bb6a78bf"}, - {file = "numpy-2.2.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:059e6a747ae84fce488c3ee397cee7e5f905fd1bda5fb18c66bc41807ff119b2"}, - {file = "numpy-2.2.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:f62aa6ee4eb43b024b0e5a01cf65a0bb078ef8c395e8713c6e8a12a697144528"}, - {file = "numpy-2.2.1-cp310-cp310-win32.whl", hash = "sha256:48fd472630715e1c1c89bf1feab55c29098cb403cc184b4859f9c86d4fcb6a95"}, - {file = "numpy-2.2.1-cp310-cp310-win_amd64.whl", hash = "sha256:b541032178a718c165a49638d28272b771053f628382d5e9d1c93df23ff58dbf"}, - {file = "numpy-2.2.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:40f9e544c1c56ba8f1cf7686a8c9b5bb249e665d40d626a23899ba6d5d9e1484"}, - {file = "numpy-2.2.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f9b57eaa3b0cd8db52049ed0330747b0364e899e8a606a624813452b8203d5f7"}, - {file = "numpy-2.2.1-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:bc8a37ad5b22c08e2dbd27df2b3ef7e5c0864235805b1e718a235bcb200cf1cb"}, - {file = "numpy-2.2.1-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:9036d6365d13b6cbe8f27a0eaf73ddcc070cae584e5ff94bb45e3e9d729feab5"}, - {file = "numpy-2.2.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:51faf345324db860b515d3f364eaa93d0e0551a88d6218a7d61286554d190d73"}, - {file = "numpy-2.2.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:38efc1e56b73cc9b182fe55e56e63b044dd26a72128fd2fbd502f75555d92591"}, - {file = "numpy-2.2.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:31b89fa67a8042e96715c68e071a1200c4e172f93b0fbe01a14c0ff3ff820fc8"}, - {file = "numpy-2.2.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:4c86e2a209199ead7ee0af65e1d9992d1dce7e1f63c4b9a616500f93820658d0"}, - {file = "numpy-2.2.1-cp311-cp311-win32.whl", hash = "sha256:b34d87e8a3090ea626003f87f9392b3929a7bbf4104a05b6667348b6bd4bf1cd"}, - {file = "numpy-2.2.1-cp311-cp311-win_amd64.whl", hash = "sha256:360137f8fb1b753c5cde3ac388597ad680eccbbbb3865ab65efea062c4a1fd16"}, - {file = "numpy-2.2.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:694f9e921a0c8f252980e85bce61ebbd07ed2b7d4fa72d0e4246f2f8aa6642ab"}, - {file = "numpy-2.2.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:3683a8d166f2692664262fd4900f207791d005fb088d7fdb973cc8d663626faa"}, - {file = "numpy-2.2.1-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:780077d95eafc2ccc3ced969db22377b3864e5b9a0ea5eb347cc93b3ea900315"}, - {file = "numpy-2.2.1-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:55ba24ebe208344aa7a00e4482f65742969a039c2acfcb910bc6fcd776eb4355"}, - {file = "numpy-2.2.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9b1d07b53b78bf84a96898c1bc139ad7f10fda7423f5fd158fd0f47ec5e01ac7"}, - {file = "numpy-2.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5062dc1a4e32a10dc2b8b13cedd58988261416e811c1dc4dbdea4f57eea61b0d"}, - {file = "numpy-2.2.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:fce4f615f8ca31b2e61aa0eb5865a21e14f5629515c9151850aa936c02a1ee51"}, - {file = "numpy-2.2.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:67d4cda6fa6ffa073b08c8372aa5fa767ceb10c9a0587c707505a6d426f4e046"}, - {file = "numpy-2.2.1-cp312-cp312-win32.whl", hash = "sha256:32cb94448be47c500d2c7a95f93e2f21a01f1fd05dd2beea1ccd049bb6001cd2"}, - {file = "numpy-2.2.1-cp312-cp312-win_amd64.whl", hash = "sha256:ba5511d8f31c033a5fcbda22dd5c813630af98c70b2661f2d2c654ae3cdfcfc8"}, - {file = "numpy-2.2.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:f1d09e520217618e76396377c81fba6f290d5f926f50c35f3a5f72b01a0da780"}, - {file = "numpy-2.2.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:3ecc47cd7f6ea0336042be87d9e7da378e5c7e9b3c8ad0f7c966f714fc10d821"}, - {file = "numpy-2.2.1-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:f419290bc8968a46c4933158c91a0012b7a99bb2e465d5ef5293879742f8797e"}, - {file = "numpy-2.2.1-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:5b6c390bfaef8c45a260554888966618328d30e72173697e5cabe6b285fb2348"}, - {file = "numpy-2.2.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:526fc406ab991a340744aad7e25251dd47a6720a685fa3331e5c59fef5282a59"}, - {file = "numpy-2.2.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f74e6fdeb9a265624ec3a3918430205dff1df7e95a230779746a6af78bc615af"}, - {file = "numpy-2.2.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:53c09385ff0b72ba79d8715683c1168c12e0b6e84fb0372e97553d1ea91efe51"}, - {file = "numpy-2.2.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:f3eac17d9ec51be534685ba877b6ab5edc3ab7ec95c8f163e5d7b39859524716"}, - {file = "numpy-2.2.1-cp313-cp313-win32.whl", hash = "sha256:9ad014faa93dbb52c80d8f4d3dcf855865c876c9660cb9bd7553843dd03a4b1e"}, - {file = "numpy-2.2.1-cp313-cp313-win_amd64.whl", hash = "sha256:164a829b6aacf79ca47ba4814b130c4020b202522a93d7bff2202bfb33b61c60"}, - {file = "numpy-2.2.1-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:4dfda918a13cc4f81e9118dea249e192ab167a0bb1966272d5503e39234d694e"}, - {file = "numpy-2.2.1-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:733585f9f4b62e9b3528dd1070ec4f52b8acf64215b60a845fa13ebd73cd0712"}, - {file = "numpy-2.2.1-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:89b16a18e7bba224ce5114db863e7029803c179979e1af6ad6a6b11f70545008"}, - {file = "numpy-2.2.1-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:676f4eebf6b2d430300f1f4f4c2461685f8269f94c89698d832cdf9277f30b84"}, - {file = "numpy-2.2.1-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:27f5cdf9f493b35f7e41e8368e7d7b4bbafaf9660cba53fb21d2cd174ec09631"}, - {file = "numpy-2.2.1-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c1ad395cf254c4fbb5b2132fee391f361a6e8c1adbd28f2cd8e79308a615fe9d"}, - {file = "numpy-2.2.1-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:08ef779aed40dbc52729d6ffe7dd51df85796a702afbf68a4f4e41fafdc8bda5"}, - {file = "numpy-2.2.1-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:26c9c4382b19fcfbbed3238a14abf7ff223890ea1936b8890f058e7ba35e8d71"}, - {file = "numpy-2.2.1-cp313-cp313t-win32.whl", hash = "sha256:93cf4e045bae74c90ca833cba583c14b62cb4ba2cba0abd2b141ab52548247e2"}, - {file = "numpy-2.2.1-cp313-cp313t-win_amd64.whl", hash = "sha256:bff7d8ec20f5f42607599f9994770fa65d76edca264a87b5e4ea5629bce12268"}, - {file = "numpy-2.2.1-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:7ba9cc93a91d86365a5d270dee221fdc04fb68d7478e6bf6af650de78a8339e3"}, - {file = "numpy-2.2.1-pp310-pypy310_pp73-macosx_14_0_x86_64.whl", hash = "sha256:3d03883435a19794e41f147612a77a8f56d4e52822337844fff3d4040a142964"}, - {file = "numpy-2.2.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4511d9e6071452b944207c8ce46ad2f897307910b402ea5fa975da32e0102800"}, - {file = "numpy-2.2.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:5c5cc0cbabe9452038ed984d05ac87910f89370b9242371bd9079cb4af61811e"}, - {file = "numpy-2.2.1.tar.gz", hash = "sha256:45681fd7128c8ad1c379f0ca0776a8b0c6583d2f69889ddac01559dfe4390918"}, + {file = "numpy-1.26.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:9ff0f4f29c51e2803569d7a51c2304de5554655a60c5d776e35b4a41413830d0"}, + {file = "numpy-1.26.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2e4ee3380d6de9c9ec04745830fd9e2eccb3e6cf790d39d7b98ffd19b0dd754a"}, + {file = "numpy-1.26.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d209d8969599b27ad20994c8e41936ee0964e6da07478d6c35016bc386b66ad4"}, + {file = "numpy-1.26.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ffa75af20b44f8dba823498024771d5ac50620e6915abac414251bd971b4529f"}, + {file = "numpy-1.26.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:62b8e4b1e28009ef2846b4c7852046736bab361f7aeadeb6a5b89ebec3c7055a"}, + {file = "numpy-1.26.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a4abb4f9001ad2858e7ac189089c42178fcce737e4169dc61321660f1a96c7d2"}, + {file = "numpy-1.26.4-cp310-cp310-win32.whl", hash = "sha256:bfe25acf8b437eb2a8b2d49d443800a5f18508cd811fea3181723922a8a82b07"}, + {file = "numpy-1.26.4-cp310-cp310-win_amd64.whl", hash = "sha256:b97fe8060236edf3662adfc2c633f56a08ae30560c56310562cb4f95500022d5"}, + {file = "numpy-1.26.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4c66707fabe114439db9068ee468c26bbdf909cac0fb58686a42a24de1760c71"}, + {file = "numpy-1.26.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:edd8b5fe47dab091176d21bb6de568acdd906d1887a4584a15a9a96a1dca06ef"}, + {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7ab55401287bfec946ced39700c053796e7cc0e3acbef09993a9ad2adba6ca6e"}, + {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:666dbfb6ec68962c033a450943ded891bed2d54e6755e35e5835d63f4f6931d5"}, + {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:96ff0b2ad353d8f990b63294c8986f1ec3cb19d749234014f4e7eb0112ceba5a"}, + {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:60dedbb91afcbfdc9bc0b1f3f402804070deed7392c23eb7a7f07fa857868e8a"}, + {file = "numpy-1.26.4-cp311-cp311-win32.whl", hash = "sha256:1af303d6b2210eb850fcf03064d364652b7120803a0b872f5211f5234b399f20"}, + {file = "numpy-1.26.4-cp311-cp311-win_amd64.whl", hash = "sha256:cd25bcecc4974d09257ffcd1f098ee778f7834c3ad767fe5db785be9a4aa9cb2"}, + {file = "numpy-1.26.4-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b3ce300f3644fb06443ee2222c2201dd3a89ea6040541412b8fa189341847218"}, + {file = "numpy-1.26.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:03a8c78d01d9781b28a6989f6fa1bb2c4f2d51201cf99d3dd875df6fbd96b23b"}, + {file = "numpy-1.26.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9fad7dcb1aac3c7f0584a5a8133e3a43eeb2fe127f47e3632d43d677c66c102b"}, + {file = "numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:675d61ffbfa78604709862923189bad94014bef562cc35cf61d3a07bba02a7ed"}, + {file = "numpy-1.26.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:ab47dbe5cc8210f55aa58e4805fe224dac469cde56b9f731a4c098b91917159a"}, + {file = "numpy-1.26.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:1dda2e7b4ec9dd512f84935c5f126c8bd8b9f2fc001e9f54af255e8c5f16b0e0"}, + {file = "numpy-1.26.4-cp312-cp312-win32.whl", hash = "sha256:50193e430acfc1346175fcbdaa28ffec49947a06918b7b92130744e81e640110"}, + {file = "numpy-1.26.4-cp312-cp312-win_amd64.whl", hash = "sha256:08beddf13648eb95f8d867350f6a018a4be2e5ad54c8d8caed89ebca558b2818"}, + {file = "numpy-1.26.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:7349ab0fa0c429c82442a27a9673fc802ffdb7c7775fad780226cb234965e53c"}, + {file = "numpy-1.26.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:52b8b60467cd7dd1e9ed082188b4e6bb35aa5cdd01777621a1658910745b90be"}, + {file = "numpy-1.26.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d5241e0a80d808d70546c697135da2c613f30e28251ff8307eb72ba696945764"}, + {file = "numpy-1.26.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f870204a840a60da0b12273ef34f7051e98c3b5961b61b0c2c1be6dfd64fbcd3"}, + {file = "numpy-1.26.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:679b0076f67ecc0138fd2ede3a8fd196dddc2ad3254069bcb9faf9a79b1cebcd"}, + {file = "numpy-1.26.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:47711010ad8555514b434df65f7d7b076bb8261df1ca9bb78f53d3b2db02e95c"}, + {file = "numpy-1.26.4-cp39-cp39-win32.whl", hash = "sha256:a354325ee03388678242a4d7ebcd08b5c727033fcff3b2f536aea978e15ee9e6"}, + {file = "numpy-1.26.4-cp39-cp39-win_amd64.whl", hash = "sha256:3373d5d70a5fe74a2c1bb6d2cfd9609ecf686d47a2d7b1d37a8f3b6bf6003aea"}, + {file = "numpy-1.26.4-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:afedb719a9dcfc7eaf2287b839d8198e06dcd4cb5d276a3df279231138e83d30"}, + {file = "numpy-1.26.4-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95a7476c59002f2f6c590b9b7b998306fba6a5aa646b1e22ddfeaf8f78c3a29c"}, + {file = "numpy-1.26.4-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:7e50d0a0cc3189f9cb0aeb3a6a6af18c16f59f004b866cd2be1c14b36134a4a0"}, + {file = "numpy-1.26.4.tar.gz", hash = "sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010"}, ] [[package]] @@ -626,6 +607,21 @@ dev = ["cython-lint (>=0.12.2)", "doit (>=0.36.0)", "mypy (==1.10.0)", "pycodest doc = ["intersphinx_registry", "jupyterlite-pyodide-kernel", "jupyterlite-sphinx (>=0.16.5)", "jupytext", "matplotlib (>=3.5)", "myst-nb", "numpydoc", "pooch", "pydata-sphinx-theme (>=0.15.2)", "sphinx (>=5.0.0,<8.0.0)", "sphinx-copybutton", "sphinx-design (>=0.4.0)"] test = ["Cython", "array-api-strict (>=2.0,<2.1.1)", "asv", "gmpy2", "hypothesis (>=6.30)", "meson", "mpmath", "ninja", "pooch", "pytest", "pytest-cov", "pytest-timeout", "pytest-xdist", "scikit-umfpack", "threadpoolctl"] +[[package]] +name = "tabulate" +version = "0.9.0" +description = "Pretty-print tabular data" +optional = false +python-versions = ">=3.7" +groups = ["main"] +files = [ + {file = "tabulate-0.9.0-py3-none-any.whl", hash = "sha256:024ca478df22e9340661486f85298cff5f6dcdba14f3813e8830015b9ed1948f"}, + {file = "tabulate-0.9.0.tar.gz", hash = "sha256:0095b12bf5966de529c0feb1fa08671671b3368eec77d7ef7ab114be2c068b3c"}, +] + +[package.extras] +widechars = ["wcwidth"] + [[package]] name = "threadpoolctl" version = "3.5.0" @@ -659,4 +655,4 @@ zstd = ["zstandard (>=0.18.0)"] [metadata] lock-version = "2.1" python-versions = ">=3.10,<4.0" -content-hash = "a0b30e32ec5f06dfab4cacd8e2f26fbca557fd73412c8223970431b42bb94a41" +content-hash = "4ecac40c978f88bbe33e294cde848a48e0c8fd627f693e0375cf3f088bcb8ef0" diff --git a/pyproject.toml b/pyproject.toml index 39abef8..a5a99cf 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -11,8 +11,10 @@ requires-python = ">=3.10,<4.0" dependencies = [ "imageio (>=2.36.1,<3.0.0)", "scikit-learn (>=1.6.1,<2.0.0)", - "easybits (>=0.1.3,<0.2.0)", - "requests (>=2.32.3,<3.0.0)" + "easybits (>=0.1.4,<0.2.0)", + "requests (>=2.32.3,<3.0.0)", + "numpy (==1.26.4)", + "tabulate (>=0.9.0,<0.10.0)" ] diff --git a/text_codecs/alphanumeric.py b/text_codecs/alphanumeric.py new file mode 100644 index 0000000..e8cc2ea --- /dev/null +++ b/text_codecs/alphanumeric.py @@ -0,0 +1,39 @@ +import string +import codecs +from custom_codecs.register import register_codec +from easybits import Bits + +allowed_characters = string.ascii_letters + string.digits + +def encode(text): + """A (very) lossy encoder which only saves ASCII letters, numbers, and spaces. + Everything else is discarded. All whitespace (e.g. tabs) is converted into spaces. + """ + ascii_characters = [] + last_character_was_space = False + for char in text: + if char in allowed_characters: + ascii_characters.append(char) + last_character_was_space = False + elif char in string.whitespace and not last_character_was_space: + ascii_characters.append(' ') + last_character_was_space = True + ascii_text = ''.join(ascii_characters) + return Bits(ascii_text).bytes + +def decode(data): + """A decoder which reads bytes and returns (string, length), + where length is the length of bytes consumed + """ + text = "" + for i, byte in enumerate(data): + try: + text += Bits(byte, length=8).ascii + except OverflowError: + print(i, byte) + print(text + '|') + print("Error") + breakpoint() + return text + +register_codec(encode, decode, "alphanumeric") diff --git a/text_codecs/ascii7.py b/text_codecs/ascii7.py new file mode 100644 index 0000000..fb24cd0 --- /dev/null +++ b/text_codecs/ascii7.py @@ -0,0 +1,33 @@ +from custom_codecs.register import register_codec +from easybits import Bits + +def encode(text): + """An encoder which only handles ASCII: non-ASCII characters + are replaced with '?'. Once all the characters are ASCII, this encoder + writes the first seven bits of each byte (the first bit of every + ASCII character is 0, so we can easily reconstruct the full byte + when we decode). Therefore, this encoder compresses ASCII text into + 7/8 of the usual size. + """ + result = Bits() + for char in text: + try: + b = Bits(char, encoding='ascii') + except UnicodeEncodeError: + b = Bits('?') + result = result.concat(b[1:]) + return result.bytes + +def decode(data): + """The matching decoder. Reads seven bits at a time, putting a 0 on + the front to create a full byte. Then converts this byte into its + ASCII representation. + """ + bits = Bits(bytes(data)) + text = "" + for i in range(0, len(bits), 7): + byte = Bits('0').concat(bits[i:i+7]) + text += Bits(byte).ascii + return text + +register_codec(encode, decode, "ascii7") diff --git a/text_codecs/register.py b/text_codecs/register.py new file mode 100644 index 0000000..763ba17 --- /dev/null +++ b/text_codecs/register.py @@ -0,0 +1,17 @@ +import codecs + +def register_codec(encode, decode, name): + """Registers a codec so that it can later be used to encode + or decode strings and bytes. + """ + def encode_wrapper(text): + return encode(text), len(text) + + def decode_wrapper(data): + return decode(data), len(data) + + def search_for_codec(query): + if query == name: + return codecs.CodecInfo(encode_wrapper, decode_wrapper, name=name) + + codecs.register(search_for_codec)