Johannes Baiter jbaiter
jbaiter
/ gist:8dd11939bedfa9d9bf7e417c86f02bd9
Created
October 27, 2016 15:40
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Thread 15 (Thread 0x7f16de535700 (LWP 23745)): | |
| #0 pthread_cond_wait@@GLIBC_2.3.2 () at ../sysdeps/unix/sysv/linux/x86_64/pthread_cond_wait.S:185 | |
| #1 0x00007f16e1b6da0b in blas_thread_server () | |
| from /home/jbaiter/.virtualenvs/dtaalign/local/lib/python2.7/site-packages/scipy/special/../.libs/libopenblasp-r0-39a31c03.2.18.so | |
| #2 0x00007f16fd6826fa in start_thread (arg=0x7f16de535700) at pthread_create.c:333 | |
| #3 0x00007f16fd3b8b5d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:109 | |
| Thread 14 (Thread 0x7f16ded36700 (LWP 23744)): | |
| #0 pthread_cond_wait@@GLIBC_2.3.2 () at ../sysdeps/unix/sysv/linux/x86_64/pthread_cond_wait.S:185 |
jbaiter
/ manifest-with-absolute-links.json
Last active
November 9, 2016 08:53
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| {"attribution":"Bayerische Staatsbibliothek","license":"https://creativecommons.org/licenses/by/3.0","logo":"https://www.bsb-muenchen.de/fileadmin/templates/images/bsb_logo.png","related":"http://daten.digitale-sammlungen.de/~db/0008/bsb00083115/images","seeAlso":[{"@id":"http://daten.digitale-sammlungen.de/~db/0008/bsb00083115/images"},{"@id":"https://opacplus.bsb-muenchen.de/title/C-560"}],"description":"Available to the public under the conditions of the Bavarian State Library.","label":"Corpus iuris civilis. Codex. Liber 1-9","sequences":[{"canvases":[{"height":7714,"images":[{"motivation":"sc:painting","on":"http://bsb0mdz-iiif1-dev.bsb.lrz.de:8080/iiif/presentation/2.0.0/bsb00083115/canvas/1","resource":{"service":{"profile":"http://iiif.io/api/image/2/level1.json","@context":"http://iiif.io/api/image/2/context.json","@id":"http://bsb0mdz-iiif1-dev.bsb.lrz.de:8080/iiif/image/2.0.0/bsb00083115_00001"},"height":7714,"width":5906,"@id":"http://bsb0mdz-iiif1-dev.bsb.lrz.de:8080/iiif/presentation/2.0.0/bsb00 |
jbaiter
/ manifest.json
Last active
November 9, 2016 08:55
Manifest with absolute links in Metadata (see .metadata[1])
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "attribution": "Bayerische Staatsbibliothek", | |
| "license": "https://creativecommons.org/licenses/by/3.0", | |
| "logo": "https://www.bsb-muenchen.de/fileadmin/templates/images/bsb_logo.png", | |
| "related": "http://daten.digitale-sammlungen.de/~db/0008/bsb00083115/images", | |
| "seeAlso": [ | |
| { | |
| "@id": "http://daten.digitale-sammlungen.de/~db/0008/bsb00083115/images" | |
| }, | |
| { |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def fetch_from_remote(url): | |
| return requests.get(url).content | |
| def content_generator(urls): | |
| with concurrent.futures.ThreadPoolExectur(max_workers=4) as pool: | |
| futs = [pool.submit(fetch_from_remote, url) for url in urls] | |
| for fut in concurrent.futures.as_completed(futs): | |
| yield fut.result() |
jbaiter
/ minimal.py
Created
December 25, 2016 23:05
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import asyncio | |
| import time | |
| from threading import Thread | |
| import aiohttp | |
| import janus | |
| # q: do i really have to pass the loop from the main thread around? | |
| async def fetch(url, loop): | |
| async with aiohttp.ClientSession(loop=loop) as session: |
jbaiter
/ CoordinateSolrHighlighter.java
Created
April 10, 2017 11:12
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| package org.apache.solr.highlight; | |
| import com.google.common.primitives.Longs; | |
| import java.io.IOException; | |
| import java.lang.invoke.MethodHandles; | |
| import java.util.ArrayList; | |
| import java.util.Collections; | |
| import java.util.HashMap; | |
| import java.util.List; | |
| import java.util.Map; |
jbaiter
/ ocr_align.py
Last active
June 12, 2017 12:57
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def align(truth_lines, ocr_lines): | |
| nonaligned = [] | |
| aligned = [] | |
| align_idx = 0 | |
| for truth_line in truth_lines: | |
| best_error = 1.0 | |
| best_align = 0 | |
| for idx, ocr_line in enumerate(ocr_lines[align_idx+1:], | |
| align_idx+1): | |
| total_error = levenshtein(truth_line, ocr_line) |
This file has been truncated, but you can view the full file.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> | |
| <html> | |
| <head> | |
| <title>OCR Output</title> | |
| <meta http-equiv='content-type' content='text/html; charset=utf-8'> | |
| <meta http-equiv='content-style-type' content='text/css'> | |
| <meta name='ocr-capabilities' content='ocr_page ocr_par ocr_cinfo ocr_line'> | |
| <meta name='ocr-system' content=' '> | |
| <meta name='ocr-number-of-pages' content='518'> | |
| <meta name='DC.title' content='Popular Tales of the West Highlands'> |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| package main | |
| import ( | |
| "archive/tar" | |
| "bytes" | |
| "compress/gzip" | |
| "encoding/json" | |
| "errors" | |
| "flag" | |
| "fmt" |
jbaiter
/ dta_aligner.py
Last active
September 28, 2017 13:51
Dependencies: `pip install click requests editdistance kraken lxml pillow-simd sickle`
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from __future__ import division | |
| import json | |
| import logging | |
| import os | |
| import re | |
| from collections import OrderedDict | |
| from io import BytesIO | |
| import click |