Add new example, fix logo background in dark mode and fix update so bumpversion works for the next release

docs/source/_static/style.css

@@ -0,0 +1,3 @@
+html[data-theme=dark] .bd-content img.stringalign-logo:not(.only-dark,.dark-light) {
+    background-color: transparent;
+}

docs/source/bibliography.bib

@@ -1,7 +1,172 @@
+@article{wick_calamari_2020,
+    title = {Calamari - {A} {High}-{Performance} {Tensorflow}-based {Deep} {Learning} {Package} for {Optical} {Character} {Recognition}},
+    volume = {14},
+    number = {2},
+    journal = {Digit. Humanit. Q.},
+    author = {Wick, Christoph and Reul, Christian and Puppe, Frank},
+    year = {2020},
+}
+
+@INPROCEEDINGS{8791206,
+  author={Nguyen, Thi-Tuyet-Hai and Jatowt, Adam and Coustaty, Mickael and Nguyen, Nhu-Van and Doucet, Antoine},
+  booktitle={2019 ACM/IEEE Jt. Conf. Digit. Libr. (JCDL)},
+  title={Deep Statistical Analysis of {OCR} Errors for Effective Post-{OCR} Processing},
+  year={2019},
+  volume={},
+  number={},
+  pages={29-38},
+  keywords={Optical character recognition software;Libraries;Feature extraction;Character recognition;Error analysis;Transducers;Statistical analysis;OCR errors, OCR post-processing, post OCR text correction},
+  doi={10.1109/JCDL.2019.00015}}
+
+@inproceedings{neudecker2019ocr,
+  title={{OCR-D}: An end-to-end open source {OCR} framework for historical printed documents},
+  author={Neudecker, Clemens and Baierer, Konstantin and Federbusch, Maria and Boenig, Matthias and W{\"u}rzner, Kay-Michael and Hartmann, Volker and Herrmann, Elisa},
+  booktitle={Proc. 3rd Int. Conf. Digit. Access Textual Cult. Herit.},
+  pages={53--58},
+  year={2019},
+  doi={10.1145/3322905.3322917}
+}
+
+@book{moran2018unicode,
+  title={The Unicode Cookbook for Linguists: Managing writing systems using orthography profiles},
+  author={Moran, Steven and Cysouw, Michael},
+  volume={10},
+  year={2018},
+  publisher={Language Science Press},
+  series={Translation and Multilingual Natural Language Processing},
+  doi={10.5281/zenodo.1300528}
+}
+
+@inproceedings{maarand2022comprehensive,
+  title={A comprehensive comparison of open-source libraries for handwritten text recognition in Norwegian},
+  author={Maarand, Martin and Beyer, Yngvil and K{\aa}sen, Andre and Fosseide, Knut T and Kermorvant, Christopher},
+  booktitle={Int. Workshop on Doc. Anal. Syst.},
+  pages={399--413},
+  year={2022},
+  organization={Springer},
+  doi={10.1007/978-3-031-06555-2_27}
+}
+
+@inproceedings{santos2019ocr,
+  title={{OCR} evaluation tools for the 21st century},
+  author={Santos, Eddie Antonio},
+  booktitle={Proc. 3rd Workshop Use Comput. Methods Study Endanger. Lang. Vol. 1 (Pap.)},
+  pages={23--27},
+  year={2019}
+}
+
+@ARTICLE{11303599,
+  author={Garrido-Munoz, Carlos and Rios-Vila, Antonio and Calvo-Zaragoza, Jorge},
+  journal={IEEE Trans. Pattern Anal. Mach. Intell.},
+  title={Handwritten Text Recognition: A Survey},
+  year={2025},
+  volume={},
+  number={},
+  pages={1-20},
+  keywords={Surveys;Complexity theory;Hidden Markov models;Text recognition;Transformers;Handwriting recognition;Deep learning;Computer architecture;Character recognition;Benchmark testing;Handwritten Text Recognition;Document Image Analysis;Document Processing;Benchmarking},
+  doi={10.1109/TPAMI.2025.3646002}}
+
+
+@inproceedings{wiechetek-etal-2024-ethical,
+    title = "The Ethical Question {--} Use of Indigenous Corpora for Large Language Models",
+    author = "Wiechetek, Linda  and
+      Pirinen, Flammie  and
+      Kappfjell, Maja Lisa  and
+      Trosterud, Trond  and
+      Gaup, B{\o}rre  and
+      Moshagen, Sjur N{\o}rsteb{\o}",
+    booktitle = "Proc. 2024 Jt. Int. Conf. Comput. Linguist. Lang. Resour. Eval. (LREC-COLING 2024)",
+    month = may,
+    year = "2024",
+    address = "Torino, Italia",
+    publisher = "ELRA and ICCL",
+    pages = "15922--15931",
+}
+
+
+@inproceedings{enstad-etal-2025-comparative,
+    title = "Comparative analysis of optical character recognition methods for {S{\'a}mi} texts from the {National} {Library} of {Norway}",
+    author = "Enstad, Tita  and
+      Trosterud, Trond  and
+      R{\o}sok, Marie Iversdatter  and
+      Beyer, Yngvil  and
+      Roald, Marie",
+    booktitle = "Proc. Jt. 25th Nord. Conf. Comput. Linguist. 11th Balt. Conf. Hum. Lang. Technol. (NoDaLiDa/Balt.-HLT 2025)",
+    month = mar,
+    year = "2025",
+    address = "Tallinn, Estonia",
+    publisher = "University of Tartu Library",
+    pages = "98--108",
+    ISBN = "978-9908-53-109-0",
+}
+
+@inproceedings{zha2023data,
+  title={Data-centric {AI}: Perspectives and challenges},
+  author={Zha, Daochen and Bhat, Zaid Pervaiz and Lai, Kwei-Herng and Yang, Fan and Hu, Xia},
+  booktitle={Proc. 2023 SIAM Int. Conf. Data Min. (SDM)},
+  pages={945--948},
+  year={2023},
+  organization={SIAM},
+  doi={10.1137/1.9781611977653.ch106}
+}
+
+@article{10.1145/2347736.2347755,
+author = {Domingos, Pedro},
+title = {A few useful things to know about machine learning},
+year = {2012},
+issue_date = {October 2012},
+publisher = {Association for Computing Machinery},
+address = {New York, NY, USA},
+volume = {55},
+number = {10},
+issn = {0001-0782},
+
+doi = {10.1145/2347736.2347755},
+abstract = {Tapping into the "folk knowledge" needed to advance machine learning applications.},
+journal = {Commun. ACM},
+month = oct,
+pages = {78–87},
+numpages = {10}
+}
+
+@article{wilkinson2016fair,
+  title={The {FAIR} Guiding Principles for scientific data management and stewardship},
+  author={Wilkinson, Mark D and Dumontier, Michel and Aalbersberg, IJsbrand Jan and Appleton, Gabrielle and Axton, Myles and Baak, Arie and Blomberg, Niklas and Boiten, Jan-Willem and da Silva Santos, Luiz Bonino and Bourne, Philip E and others},
+  journal={Sci. data},
+  volume={3},
+  number={160018},
+  pages={1--9},
+  year={2016},
+  publisher={Nature Publishing Group},
+  doi={10.1038/sdata.2016.18}
+}
+
+@article{barker2022introducing,
+  title={Introducing the {FAIR} Principles for research software},
+  author={Barker, Michelle and Chue Hong, Neil P and Katz, Daniel S and Lamprecht, Anna-Lena and Martinez-Ortiz, Carlos and Psomopoulos, Fotis and Harrow, Jennifer and Castro, Leyla Jael and Gruenpeter, Morane and Martinez, Paula Andrea and others},
+  journal={Sci. data},
+  volume={9},
+  number={622},
+  pages={1--6},
+  year={2022},
+  publisher={Nature Publishing Group UK London},
+  doi={10.1038/s41597-022-01710-x}
+}
+
+@inproceedings{neudecker2021survey,
+  title={A survey of {OCR} evaluation tools and metrics},
+  author={Neudecker, Clemens and Baierer, Konstantin and Gerber, Mike and Clausner, Christian and Antonacopoulos, Apostolos and Pletschacher, Stefan},
+  booktitle={Proc. 6th Int. Workshop Hist. Doc. Imaging Process. (HIP '21)},
+  pages={13--18},
+  year={2021},
+  doi={10.1145/3476887.3476888}
+}
+
 @techreport{unicode-standard,
-	title = {The Unicode® Standard Version 17.0 – Core Specification},
+	title = {The {Unicode}® Standard Version 17.0},
+    type = {Core Specification},
 	url = {https://www.unicode.org/versions/Unicode17.0.0/core-spec/},
-	author = {Unicode Consortium},
+	author = {{Unicode Consortium}},
 	institution = {Unicode Consortium},
 	month = sep,
 	year = {2025}
@@ -14,8 +179,8 @@ @techreport{unicode-annex-15
 	url = {https://unicode.org/reports/tr15/},
 	number = {UAX \#15},
 	urldate = {2025-07-30},
-	institution = {Unicode Consortium},
-	author = {Unicode Consortium},
+	institution = {{Unicode Consortium}},
+	author = {{Unicode Consortium}},
 	editor = {Whistler, Ken},
 	month = jul,
 	year = {2025},
@@ -26,9 +191,9 @@ @techreport{unicode-annex-29
 	title = {Unicode Text Segmentation},
 	url = {https://unicode.org/reports/tr29/},
 	number = {UAX \#29},
-	urldate = {2025-09-22},
-	institution = {Unicode Consortium},
-	author = {Unicode Consortium},
+	urldate = {2025-08-17},
+	institution = {{Unicode Consortium}},
+	author = {{Unicode Consortium}},
 	editor = {Hadley, Josh},
 	month = aug,
 	year = {2025},
@@ -40,8 +205,8 @@ @techreport{unicode-annex-39
 	url = {https://unicode.org/reports/tr39/},
 	number = {UAX \#39},
 	urldate = {2025-09-04},
-	institution = {Unicode Consortium},
-	author = {Unicode Consortium},
+	institution = {{Unicode Consortium}},
+	author = {{Unicode Consortium}},
 	editor = {Davis, Mark and Suignard, Michel},
 	month = sep,
 	year = {2025},
@@ -52,25 +217,25 @@ @techreport{unicode-annex-51
 	title = {Unicode Emoji},
 	url = {https://www.unicode.org/reports/tr51/},
 	number = {UAX \#51},
-	urldate = {2025-10-09},
-	institution = {Unicode Consortium},
-	author = {Unicode Consortium},
+	urldate = {2025-09-04},
+	institution = {{Unicode Consortium}},
+	author = {{Unicode Consortium}},
 	editor = {Davis, Mark and Holbrook, Ned},
 	month = oct,
 	year = {2025},
 }
 
+
 @article{navarro_guided_2001,
 	title = {A guided tour to approximate string matching},
 	volume = {33},
 	issn = {0360-0300, 1557-7341},
-	url = {https://dl.acm.org/doi/10.1145/375360.375365},
 	doi = {10.1145/375360.375365},
 	abstract = {We survey the current techniques to cope with the problem of string matching that allows errors. This is becoming a more and more relevant issue for many fast growing areas such as information retrieval and computational biology. We focus on online searching and mostly on edit distance, explaining the problem and its relevance, its statistical behavior, its history and current developments, and the central ideas of the algorithms and their complexities. We present a number of experiments to compare the performance of the different algorithms and show which are the best choices. We conclude with some directions for future work and open problems.},
 	language = {en},
 	number = {1},
 	urldate = {2025-10-04},
-	journal = {ACM Computing Surveys},
+	journal = {ACM Comput. Surv.},
 	author = {Navarro, Gonzalo},
 	month = mar,
 	year = {2001},
@@ -80,10 +245,78 @@ @article{navarro_guided_2001
 @article{needleman1970general,
   title={A general method applicable to the search for similarities in the amino acid sequence of two proteins},
   author={Needleman, Saul B and Wunsch, Christian D},
-  journal={Journal of molecular biology},
+  journal={J. Mol. Biol.},
   volume={48},
   number={3},
   pages={443--453},
   year={1970},
-  publisher={Elsevier}
+  publisher={Elsevier},
+  doi={10.1016/0022-2836(70)90057-4}
+}
+
+@article{levenshtein1965binary,
+  title={Binary codes capable of correcting spurious insertions and deletions of ones},
+  author={Levenshtein, Vladimir},
+  journal={Probl. Inf. Transm.},
+  volume={1},
+  pages={8--17},
+  year={1965}
+}
+
+@article{levenshtein1966binary,
+  title={Binary codes capable of correcting deletions, insertions and reversals},
+  author={Levenshtein, Vladimir},
+  journal={Sov. Phys. Dokl.},
+  volume={10},
+  number={8},
+  pages={707--710},
+  year={1966},
+  note={Original in Russian in Dokl. Akad. Nauk SSSR 163, 4, 845–848, 1965}
+}
+
+@techreport{rice1996isri,
+  title={The {ISRI} analytic tools for {OCR} evaluation Version 5.1},
+  author={Rice, Stephen V and Nartker, Thomas A},
+  institution={Information Science Research Institute},
+  number={TR-96-02},
+  year={1996}
+}
+
+@article{UKKONEN1985100,
+title = {Algorithms for approximate string matching},
+journal = {Inf. Control},
+volume = {64},
+number = {1},
+pages = {100-118},
+year = {1985},
+issn = {0019-9958},
+doi = {10.1016/S0019-9958(85)80046-2},
+author = {Esko Ukkonen}
+}
+
+@inproceedings{10.1145/2501115.2501130,
+author = {Papadopoulos, Christos and Pletschacher, Stefan and Clausner, Christian and Antonacopoulos, Apostolos},
+title = {The {IMPACT} dataset of historical document images},
+year = {2013},
+isbn = {9781450321150},
+publisher = {ACM},
+doi = {10.1145/2501115.2501130},
+booktitle = {Proc. 2nd Int. Workshop Hist. Doc. Imaging Process. (HIP '13)},
+pages = {123–130},
+numpages = {8},
+keywords = {historical documents, ground truth production, dataset production},
+location = {Washington, District of Columbia, USA}
+}
+
+@article{Springmann_Reul_Dipper_Baiter_2018,
+title={Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin},
+volume={33},
+url={https://jlcl.org/article/view/220},
+DOI={10.21248/jlcl.33.2018.220},
+number={1},
+journal={Journal for Language Technology and Computational Linguistics},
+author={Springmann, Uwe and Reul, Christian and Dipper, Stefanie and Baiter, Johannes},
+year={2018},
+month={Jul.},
+pages={97--114}
 }

docs/source/conf.py

@@ -43,6 +43,8 @@
 html_logo = "images/bunting_flat.svg"
 html_favicon = "images/favicon.svg"
 html_title = "Stringalign"
+html_static_path = ["_static"]
+html_css_files = ["style.css"]
 
 nbsphinx_execute = "always"
 nbsphinx_allow_errors = False

docs/source/index.rst

@@ -2,6 +2,7 @@ Stringalign
 ===========
 
 .. image:: images/logo_flat.svg
+   :class: stringalign-logo
    :width: 600px
    :alt: Two cute caterpillars dancing under bunting with the letters 'STRING ALIGN'