funkpower/catena
1
0
Fork 0
mirror of https://git.pumpin.online/funkpower/catena.git synced 2026-10-23 03:07:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

pdftriage: text layer verdicts, including the reflected-font recovery

Browse Source
This commit is contained in:
funkpower
2026-09-19 11:46:34 -04:00
parent bd0ae11d01
commit 33c2e40a1a
16 changed files with 1465 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
parity/golden/pdftriage/samples.ndjson
+24
View File
@@ -0,0 +1,24 @@
{"ascii": 0.0, "body": 0, "decoded": null, "english": null, "latin1": 0.0, "letters": 0.0, "name": "empty", "tidy": null, "vowelled": null}
{"ascii": 0.0, "body": 0, "decoded": null, "english": null, "latin1": 0.0, "letters": 0.0, "name": "whitespace", "tidy": null, "vowelled": null}
{"ascii": 1.0, "body": 29, "decoded": null, "english": null, "latin1": 0.0, "letters": 0.9655172413793104, "name": "prose-short", "tidy": null, "vowelled": null}
{"ascii": 1.0, "body": 1104, "decoded": null, "english": 0.42105263157894735, "latin1": 0.0, "letters": 0.9782608695652174, "name": "prose", "tidy": 1.0, "vowelled": 1.0}
{"ascii": 0.0, "body": 1104, "decoded": "The second estate held its land in exchange for service, and the service was military. That much is agreed; what follows is not. The court rolls do not say how often the obligation was tested, because the clerk who recorded it had no vocabulary for the difference between a rebellion and a bad harvest. This is the central difficulty of the sources, and everything that follows depends on reading around that limitation rather than through it. The second estate held its land in exchange for service, and the service was military. That much is agreed; what follows is not. The court rolls do not say how often the obligation was tested, because the clerk who recorded it had no vocabulary for the difference between a rebellion and a bad harvest. This is the central difficulty of the sources, and everything that follows depends on reading around that limitation rather than through it. The second estate held its land in exchange for service, and the service was military. That much is agreed; what follows is not. The court rolls do not say how often the obligation was tested, because the clerk who recorded it had no vocabulary for the difference between a rebellion and a bad harvest. This is the central difficulty of the sources, and everything that follows depends on reading around that limitation rather than through it. ", "english": 0.0, "latin1": 1.0, "letters": 0.07608695652173914, "name": "prose-reflected", "tidy": null, "vowelled": null}
{"ascii": 0.0, "body": 368, "decoded": "The second estate held its land in exchange for service, and the service was military. That much is agreed; what follows is not. The court rolls do not say how often the obligation was tested, because the clerk who recorded it had no vocabulary for the difference between a rebellion and a bad harvest. This is the central difficulty of the sources, and everything that follows depends on reading around that limitation rather than through it. ", "english": null, "latin1": 1.0, "letters": 0.07608695652173914, "name": "prose-reflected-short", "tidy": null, "vowelled": null}
{"ascii": 0.9740932642487047, "body": 579, "decoded": null, "english": 0.0, "latin1": 0.025906735751295335, "letters": 0.9740932642487047, "name": "german", "tidy": 1.0, "vowelled": 1.0}
{"ascii": 0.0, "body": 579, "decoded": "Die Grundherrschaft war kein Eigentum im r*mischen Sinne, sondern ein B$ndel von Anspr$chen. Die Bauern schuldeten Abgaben und Frondienste; der Herr schuldete Schutz. Dber die H<ufigkeit der Konflikte schweigen die Quellen. Die Grundherrschaft war kein Eigentum im r*mischen Sinne, sondern ein B$ndel von Anspr$chen. Die Bauern schuldeten Abgaben und Frondienste; der Herr schuldete Schutz. Dber die H<ufigkeit der Konflikte schweigen die Quellen. Die Grundherrschaft war kein Eigentum im r*mischen Sinne, sondern ein B$ndel von Anspr$chen. Die Bauern schuldeten Abgaben und Frondienste; der Herr schuldete Schutz. Dber die H<ufigkeit der Konflikte schweigen die Quellen. ", "english": 0.0, "latin1": 1.0, "letters": 0.16580310880829016, "name": "german-reflected", "tidy": null, "vowelled": null}
{"ascii": 0.025, "body": 240, "decoded": null, "english": null, "latin1": 0.0, "letters": 0.975, "name": "greek", "tidy": null, "vowelled": null}
{"ascii": 0.125, "body": 240, "decoded": null, "english": null, "latin1": 0.0, "letters": 0.875, "name": "cyrillic", "tidy": null, "vowelled": null}
{"ascii": 1.0, "body": 348, "decoded": null, "english": 0.0, "latin1": 0.0, "letters": 0.4482758620689655, "name": "chess", "tidy": null, "vowelled": null}
{"ascii": 1.0, "body": 136, "decoded": null, "english": null, "latin1": 0.0, "letters": 0.8823529411764706, "name": "running-heads", "tidy": null, "vowelled": null}
{"ascii": 0.7878787878787878, "body": 660, "decoded": null, "english": 0.0, "latin1": 0.0, "letters": 0.8181818181818182, "name": "combining-letters", "tidy": null, "vowelled": null}
{"ascii": 0.0, "body": 800, "decoded": null, "english": null, "latin1": 1.0, "letters": 0.685, "name": "nonsense-latin1", "tidy": null, "vowelled": null}
{"ascii": 0.0, "body": 800, "decoded": null, "english": null, "latin1": 1.0, "letters": 0.685, "name": "nonsense-reflected", "tidy": null, "vowelled": null}
{"ascii": 0.8675324675324675, "body": 770, "decoded": null, "english": 0.1917808219178082, "latin1": 0.012987012987012988, "letters": 0.9662337662337662, "name": "mixed-scripts", "tidy": 1.0, "vowelled": 1.0}
{"ascii": 1.0, "body": 280, "decoded": null, "english": null, "latin1": 0.0, "letters": 1.0, "name": "all-caps", "tidy": 1.0, "vowelled": 1.0}
{"ascii": 1.0, "body": 1080, "decoded": null, "english": 0.0, "latin1": 0.0, "letters": 0.7777777777777778, "name": "mixed-case-junk", "tidy": 0.0, "vowelled": 0.25}
{"ascii": 1.0, "body": 400, "decoded": null, "english": null, "latin1": 0.0, "letters": 0.0, "name": "digits", "tidy": null, "vowelled": null}
{"ascii": 1.0, "body": 520, "decoded": null, "english": null, "latin1": 0.0, "letters": 0.0, "name": "punctuation", "tidy": null, "vowelled": null}
{"ascii": 1.0, "body": 564, "decoded": null, "english": 0.4166666666666667, "latin1": 0.0, "letters": 0.9361702127659575, "name": "emdash-prose", "tidy": 1.0, "vowelled": 1.0}
{"ascii": 1.0, "body": 736, "decoded": null, "english": 0.42105263157894735, "latin1": 0.0, "letters": 0.9782608695652174, "name": "nbsp-prose", "tidy": 1.0, "vowelled": 1.0}
{"ascii": 0.9523809523809523, "body": 630, "decoded": null, "english": 0.0, "latin1": 0.0, "letters": 0.9523809523809523, "name": "control-chars", "tidy": 1.0, "vowelled": 1.0}
{"ascii": 0.8823529411764706, "body": 680, "decoded": null, "english": 0.5, "latin1": 0.0, "letters": 0.9705882352941176, "name": "ligatures", "tidy": 1.0, "vowelled": 0.875}