X-Git-Url: http://gitweb.fperrin.net/?p=gen-quickdic.git;a=blobdiff_plain;f=OPTED_to_tab_separated;fp=OPTED_to_tab_separated;h=479b3f0c5479ecd3ac345179ebb48b6033656eb0;hp=0000000000000000000000000000000000000000;hb=5da87a9ec2370bb2f7ce11e107f07625e42f7171;hpb=5598132b30a07363a5b2d1b9966c761150614158

diff --git a/OPTED_to_tab_separated b/OPTED_to_tab_separated
new file mode 100755
index 0000000..479b3f0
--- /dev/null
+++ b/OPTED_to_tab_separated
@@ -0,0 +1,109 @@
+#!/usr/bin/python3
+
+from html.parser import HTMLParser
+from glob import glob
+
+class OptedParser(HTMLParser):
+    def __init__(self):
+        super().__init__()
+        self.reading_headword = False
+        self.reading_pos = False
+        self.reading_definition = False
+        self.headword = ""
+        self.pos = ""
+        self.definition = ""
+        self.entries = {}
+
+    def _add_definition(self, headword, definition):
+        if headword not in self.entries:
+            self.entries[headword] = []
+        self.entries[headword] += [definition]
+
+    def write_definitions(self, outputfile):
+        for headword in self.entries:
+            if len(self.entries[headword]) == 1:
+                outputfile.write(f"{headword}\t{self.entries[headword][0]}\n")
+            else:
+                outputfile.write(f"{headword}\t<ol>")
+                for entry in self.entries[headword]:
+                    outputfile.write(f"<li>{entry}</li>")
+                outputfile.write(f"</ol>\n")
+            if " " in headword or "-" in headword:
+                print(f"<{headword}> has space or dash")
+
+    def handle_starttag(self, tag, attrs):
+        if tag == "b":
+            assert not self.reading_headword
+            assert not self.reading_pos
+            assert not self.reading_definition
+            assert not self.headword
+
+            self.reading_headword = True
+
+        elif tag == "i":
+            assert not self.reading_headword
+            assert not self.reading_pos
+            assert not self.pos
+
+            self.reading_pos = True
+
+    def handle_data(self, data):
+        if self.reading_headword:
+            self.headword += data.lower()
+        elif self.reading_pos:
+            self.pos += data
+        elif self.reading_definition:
+            self.definition += data
+
+    def handle_endtag(self, tag):
+        if tag == "b":
+            assert self.reading_headword
+            assert not self.reading_definition
+            assert not self.reading_pos
+
+            self.reading_headword = False
+            self.reading_definition = True
+
+        elif tag == "i":
+            assert not self.reading_headword
+            assert self.reading_pos
+            assert self.reading_definition
+
+            self.reading_pos = False
+
+        elif tag == "p":
+            assert not self.reading_headword
+            assert self.reading_definition
+            assert not self.reading_pos
+            assert self.headword
+            assert self.definition
+
+            if self.pos:
+                self.definition = f"(<i>{self.pos}</i>) {self.definition}"
+            self.definition = self.definition.replace("()", "")
+            self.definition = self.definition.strip()
+
+            assert not "\\" in self.headword, f"\\ for word {self.headword}"
+            if any(str(digit) in self.headword for digit in range(10)):
+                print(f"Warning: {self.headword} has digits")
+
+            self._add_definition(self.headword, self.definition)
+            self.reading_definition = False
+            self.headword = ""
+            self.pos = ""
+            self.definition = ""
+
+def main():
+    opted_parser = OptedParser()
+    for fname in glob("OPTED/v003/wb1913_*.html"):
+        print(f"Running on {fname}")
+        with open(fname, mode="r",
+                  encoding="macroman", errors="strict") as inputfile:
+            opted_parser.feed(inputfile.read())
+
+    with open("OPTED.tab_separated", "w", encoding="utf-8") as outputfile:
+        opted_parser.write_definitions(outputfile)
+
+
+if __name__ == "__main__":
+    main()