Store cmap's as json

pdfminer · Jan 27, 2024 · e266243 · e266243
1 parent 45e8443
commit e266243
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 15 deletions.
diff --git a/Makefile b/Makefile
@@ -9,21 +9,21 @@ MKDIR=mkdir
 CONV_CMAP=$(PYTHON) tools/conv_cmap.py
 CMAPSRC=cmaprsrc
 CMAPDST=pdfminer/cmap
-cmap: $(CMAPDST)/to-unicode-Adobe-CNS1.pickle.gz $(CMAPDST)/to-unicode-Adobe-GB1.pickle.gz \
-	$(CMAPDST)/to-unicode-Adobe-Japan1.pickle.gz $(CMAPDST)/to-unicode-Adobe-Korea1.pickle.gz
+cmap: $(CMAPDST)/to-unicode-Adobe-CNS1.json.gz $(CMAPDST)/to-unicode-Adobe-GB1.json.gz \
+	$(CMAPDST)/to-unicode-Adobe-Japan1.json.gz $(CMAPDST)/to-unicode-Adobe-Korea1.json.gz
 cmap_clean:
 	-$(RM) -r $(CMAPDST)
 $(CMAPDST):
 	$(MKDIR) $(CMAPDST)
-$(CMAPDST)/to-unicode-Adobe-CNS1.pickle.gz: $(CMAPDST)
+$(CMAPDST)/to-unicode-Adobe-CNS1.json.gz: $(CMAPDST)
 	$(CONV_CMAP) -c B5=cp950 -c UniCNS-UTF8=utf-8 \
 		$(CMAPDST) Adobe-CNS1 $(CMAPSRC)/cid2code_Adobe_CNS1.txt
-$(CMAPDST)/to-unicode-Adobe-GB1.pickle.gz: $(CMAPDST)
+$(CMAPDST)/to-unicode-Adobe-GB1.json.gz: $(CMAPDST)
 	$(CONV_CMAP) -c GBK-EUC=cp936 -c UniGB-UTF8=utf-8 \
 		$(CMAPDST) Adobe-GB1 $(CMAPSRC)/cid2code_Adobe_GB1.txt
-$(CMAPDST)/to-unicode-Adobe-Japan1.pickle.gz: $(CMAPDST)
+$(CMAPDST)/to-unicode-Adobe-Japan1.json.gz: $(CMAPDST)
 	$(CONV_CMAP) -c RKSJ=cp932 -c EUC=euc-jp -c UniJIS-UTF8=utf-8 \
 		$(CMAPDST) Adobe-Japan1 $(CMAPSRC)/cid2code_Adobe_Japan1.txt
-$(CMAPDST)/to-unicode-Adobe-Korea1.pickle.gz: $(CMAPDST)
+$(CMAPDST)/to-unicode-Adobe-Korea1.json.gz: $(CMAPDST)
 	$(CONV_CMAP) -c KSC-EUC=euc-kr -c KSC-Johab=johab -c KSCms-UHC=cp949 -c UniKS-UTF8=utf-8 \
 		$(CMAPDST) Adobe-Korea1 $(CMAPSRC)/cid2code_Adobe_Korea1.txt
diff --git a/tools/conv_cmap.py b/tools/conv_cmap.py
@@ -2,7 +2,7 @@
 import argparse
 import codecs
 import gzip
-import pickle as pickle
+import json
 import sys
 from pathlib import Path
 from typing import List, Any
@@ -140,16 +140,14 @@ def dump_cmap(self, fp, enc):
             IS_VERTICAL=self.is_vertical.get(enc, False),
             CODE2CID=self.code2cid.get(enc),
         )
-        fp.write(pickle.dumps(data, 2))
-        return
+        json.dump(data, fp)
 
     def dump_unicodemap(self, fp):
         data = dict(
             CID2UNICHR_H=self.cid2unichr_h,
             CID2UNICHR_V=self.cid2unichr_v,
         )
-        fp.write(pickle.dumps(data, 2))
-        return
+        json.dump(data, fp)
 
 
 def create_parser() -> argparse.ArgumentParser:
@@ -195,14 +193,14 @@ def main(argv: List[Any]):
 
     outdir.mkdir(exist_ok=True)
     for enc in converter.get_encs():
-        path = outdir / f"{enc}.pickle.gz"
+        path = outdir / f"{enc}.json.gz"
         print(f"writing: {path}...")
-        with gzip.open(path, "wb") as fp:
+        with gzip.open(path, "wt") as fp:
             converter.dump_cmap(fp, enc)
 
-    path = outdir / f"to-unicode-{regname}.pickle.gz"
+    path = outdir / f"to-unicode-{regname}.json.gz"
     print(f"writing: {path}...")
-    with gzip.open(path, "wb") as fp:
+    with gzip.open(path, "wt") as fp:
         converter.dump_unicodemap(fp)