From 27ae0b4c6d571104f553d5bf863998fd478feb45 Mon Sep 17 00:00:00 2001 From: Ian Jackson Date: Sat, 20 Jun 2009 10:14:45 +0100 Subject: [PATCH] Rename yppsc-ocr-resolver to dictionary-manager, and database and charset to dictionary, in docs etc. too --- pctb/README | 9 +++++---- pctb/{README.charset => README.dictionary} | 20 +++++++++---------- pctb/convert.c | 4 ++-- ...{yppsc-ocr-resolver => dictionary-manager} | 0 pctb/resolve.c | 4 ++-- 5 files changed, 19 insertions(+), 18 deletions(-) rename pctb/{README.charset => README.dictionary} (89%) rename pctb/{yppsc-ocr-resolver => dictionary-manager} (100%) diff --git a/pctb/README b/pctb/README index 9402240..1261296 100644 --- a/pctb/README +++ b/pctb/README @@ -27,7 +27,7 @@ Options to vary the processing: --quiet Suppress progress messages --screenshot-file F Store or read screenshots in F rather than #pages#.pnm --window-id ID Specified X window is the YPP client - do not search - --edit-charset Enable character set editing. See README.charset. + --edit-dictionary Enable dictionary editing. See README.dictionary. Controlling what happens to the results: --upload (default) Upload to the PCTB server @@ -58,9 +58,9 @@ The program reads and writes the following files: * charset-15.txt - Character set database. For the semantics of the contents of this + Character set dictionary. For the semantics of the contents of this file see README.charset. There is not currently any accurate - documentation of this database format. + documentation of this dictionary format. If you delete this file you'll have to re-enter a lot of glyph data (and probably get it wrong and make the program misrecognise @@ -73,9 +73,10 @@ The program reads and writes the following files: Map from commodity names to the numbers required by the PCTB server. This is fetched and updated automatically as necessary. It can safely be deleted as it will then be refetched. + * .new - When any of these tools overwrite one of the persistent database + When any of these tools overwrite one of the persistent dictionary files, they temporarily write to .new. These files are all in the current working directory. There is not diff --git a/pctb/README.charset b/pctb/README.dictionary similarity index 89% rename from pctb/README.charset rename to pctb/README.dictionary index f2bfc7d..4fdc37d 100644 --- a/pctb/README.charset +++ b/pctb/README.dictionary @@ -5,7 +5,7 @@ Sometimes the OCR will not be able to recognise some text. By default, when this happens, the program will stop with a fatal error and refer you to this document. -It is possible to fix this by editing the character set database used +It is possible to fix this by editing the character set dictionary used by the OCR algorithm. But, it is important to get these inputs right or your client may misrecognise text in future. You *must* read the documentation here first. @@ -19,7 +19,7 @@ of `glyph' bitmaps, against the bitmap in each cell in the commodity table. We match from left to right. We do not insist that each glyph is followed by whitespace, and nor do -we insist that glyphs do not contain whitespace. Our glyph database +we insist that glyphs do not contain whitespace. Our glyph dictionary can contain entries which are strict prefixes of other entries - that is, a glyph for (say) `v' which is the leftmost part of another glyph for (say) `w'. We resolve these ambiguities by taking the longest @@ -29,7 +29,7 @@ So you should not be surprised if the program has matched the left-hand half of some letter and thinks it is a different letter. If the part that it did recognise does look like the letter in question, that isn't wrong. All you need to do is insert the whole of the -actual letter in the database - move the LH cursor to the start of the +actual letter in the dictionary - move the LH cursor to the start of the letter, and the RH cursor to its end, and hit `return' and enter the correct character. The longest match rule will mean it will prefer the entry you have just made. @@ -38,7 +38,7 @@ the entry you have just made. Upper vs lower case - important note regarding `l' and `I' ---------------------------------------------------------- -We maintain separate databases for upper and lower case. At the +We maintain separate dictionaries for upper and lower case. At the beginning of each cell in the table, we expect uppercase; in the middle of a word we expect lowercase; and, unfortunately, after an inter-word gap, we are not sure. @@ -47,12 +47,12 @@ This is troublesome because `l' and `I' look identical on the screen. So any time we see a word starting with `l' or `I', the program has to ask about it. -*Do not* make an entry in the character set database mapping `vertical +*Do not* make an entry in the character set dictionary mapping `vertical stick' to `l' or `I'. Instead, select enough of the whole word in question that no word would start with the other letter, and enter the whole word or part of it as a new glyph. -For example, in the supplied database there is already a glyph for +For example, in the supplied dictionary there is already a glyph for `Iron'; this is OK because there are no words which start `lron'. Do not make an entry for a string more than 7 characters long; @@ -72,7 +72,7 @@ recognised as. *You should check the alleged context before entering a character*. If it is wrong, you should fix it, rather that just making an entry -for the uppercase letter in the lowercase database. +for the uppercase letter in the lowercase dictionary. Instead, make a new glyph for the last letter of the previous word plus the (unusually narrow) inter-word space, and end that entry with @@ -100,9 +100,9 @@ containing `yw' and define it as `yw'. Fixing mistakes --------------- -The OCR query UI allows you to delete things from the glyph database. +The OCR query UI allows you to delete things from the glyph dictionary. However since you are not guaranteed to actually get an OCR query at -all if the database contains errors, you shouldn't rely on this. +all if the dictionary contains errors, you shouldn't rely on this. If you think you have made mistakes answering OCR queries (for example, the recognised data is wrong), you should download a fresh @@ -123,7 +123,7 @@ and in future, just always run it with the --edit-charset option. With --edit-charset, when the OCR finds characters it does not understand, it will put up an OCR resolution query window. This will display the part of the text it is having trouble with, showing where -it has got to, and allow you to edit the character set database it +it has got to, and allow you to edit the character set dictionary it uses for recognising the text. *This is subtle* and it is important to understand the way the diff --git a/pctb/convert.c b/pctb/convert.c index dd7f5d1..4cc45b4 100644 --- a/pctb/convert.c +++ b/pctb/convert.c @@ -121,8 +121,8 @@ int main(int argc, char **argv) { o_single_page= 1; else if (!strcmp(arg,"--quiet")) o_quiet= 1; - else if (!strcmp(arg,"--edit-charset")) - o_resolver= "./yppsc-ocr-resolver"; + else if (!strcmp(arg,"--edit-dictionary")) + o_resolver= "./dictionary-manager"; else if (!strcmp(arg,"--raw-tsv")) o_outputmode= 0; else if (!strcmp(arg,"--upload") || diff --git a/pctb/yppsc-ocr-resolver b/pctb/dictionary-manager similarity index 100% rename from pctb/yppsc-ocr-resolver rename to pctb/dictionary-manager diff --git a/pctb/resolve.c b/pctb/resolve.c index 052ec32..2c61e3b 100644 --- a/pctb/resolve.c +++ b/pctb/resolve.c @@ -52,7 +52,7 @@ FILE *resolve_start(void) { DEBUGP(callout) ? "--debug" : "--noop-arg", "--automatic-1", (char*)0); - sysassert(!"execlp ocr-resolver failed"); + sysassert(!"execlp dictionary-manager failed"); } sysassert(! close(jobpipe[0]) ); sysassert(! close(donepipe[1]) ); @@ -78,7 +78,7 @@ void resolve_finish(void) { } if (r==0) { - waitpid_check_exitstatus(resolver_pid, "character resolver"); + waitpid_check_exitstatus(resolver_pid, "dictionary manager"); fclose(resolver); close(resolver_done); resolver= 0; -- 2.30.2