bpf-developer-tutorial/third_party/blazesym/scripts/gen-one-page.py

'''Generate one page API document from rustdoc.

This script parses HTML files generated by rustoc and generates a single page API
document.

'''
from html.parser import HTMLParser

pages = ['index.html',
         'struct.BlazeSymbolizer.html',
         'struct.SymbolizedResult.html',
         'enum.SymbolSrcCfg.html',
         'enum.SymbolizerFeature.html',
         'fn.blazesym_new.html',
         'fn.blazesym_free.html',
         'fn.blazesym_symbolize.html',
         'fn.blazesym_result_free.html',
         'struct.blazesym.html',
         'struct.sym_src_cfg.html',
         'enum.blazesym_src_type.html',
         'union.ssc_params.html',
         'struct.ssc_elf.html',
         'struct.ssc_kernel.html',
         'struct.ssc_process.html',
         'struct.blazesym_result.html',
         'struct.blazesym_entry.html',
         'struct.blazesym_csym.html',
         ]

def replace_text(src, replace, start, stop):
    lines = src.split('\n')
    if start[0] == stop[0]:
        lineno = start[0]
        lines[lineno] = lines[lineno][:start[1]] + replace + lines[lineno][stop[1]:]
    else:
        lines[start[0]] = lines[start[0]][:start[1]]
        lines[stop[0]] = lines[stop[0]][stop[1]:]
        lines[start[0] + 1: stop[0]] = [replace]
        pass
    return '\n'.join(lines)

class MyParser(HTMLParser):
    def get_doc_range(self, start, end):
        lines = self.raw_data.split('\n')
        lines = lines[start[0] - 1: end[0]]
        lines[-1] = lines[-1][:end[1]]
        lines[0] = lines[0][start[1]:]
        content = '\n'.join(lines)
        if hasattr(self, 'replaces'):
            for replace, rstart, rstop in reversed(self.replaces):
                rstart = list(rstart)
                rstop = list(rstop)
                rstart[0] -= start[0]
                rstop[0] -= start[0]
                if rstart[0] == 0:
                    rstart[1] -= start[1]
                    pass
                if rstop[0] == 0:
                    rstop[1] -= start[1]
                    pass
                content = replace_text(content, replace, rstart, rstop)
                pass
            pass
        return content

    def get_pos_end_tag(self):
        pos = self.getpos()
        lines = self.raw_data.split('\n')
        line = lines[pos[0] - 1]
        col = line.find('>', pos[1]) + 1
        return (pos[0], col)

    def handle_starttag(self, tag, attrs):
        attrs = dict(attrs)
        if tag == 'body':
            self.doc_type = attrs['class'].split()[-1]
        elif tag == 'section' and 'id' in attrs and attrs['id'] == 'main-content':
            if self.doc_type == 'crate':
                self.start_pos = self.getpos()
            elif self.doc_type in ('struct', 'enum', 'union'):
                if not hasattr(self, 'start_pos'):
                    self.start_pos = self.getpos()
                    pass
                pass
            elif self.doc_type == 'fn':
                if not hasattr(self, 'start_pos'):
                    self.start_pos = self.getpos()
                    pass
                pass
            pass
        elif 'class' in attrs and 'example-wrap' in attrs['class'].split():
            self.replacing = '&nbsp;&nbsp;......&lt;&lt;EXAMPLE&gt;&gt......<br/>'
            self.replace_depth = 0
            self.replace_start = self.getpos();
        elif 'class' in attrs and 'item-decl' in attrs['class'].split():
            self.replacing = '&nbsp;&nbsp;......&lt;&lt;DECLARATION&gt;&gt;......<br/>'
            self.replace_depth = 0
            self.replace_start = self.getpos()
        elif hasattr(self, 'replace_depth'):
            self.replace_depth += 1
        elif hasattr(self, 'depth'):
            self.depth += 1
            pass
        elif hasattr(self, 'start_pos'):
            if self.doc_type in ('struct', 'enum', 'union'):
                if 'id' in attrs and attrs['id'].endswith('implementations'):
                    print('%s\n</section>' % self.get_doc_range(self.start_pos, self.getpos()))
                    self.doc_type = ''
                    pass
            elif self.doc_type == 'fn' and not hasattr(self, 'depth'):
                self.depth = 0
                pass
            elif self.doc_type == 'crate' and 'class' in attrs and attrs['class'].endswith('top-doc'):
                self.depth = 0
                pass
            pass
        pass

    def handle_endtag(self, tag):
        if hasattr(self, 'replace_depth'):
            if self.replace_depth > 0:
                self.replace_depth -= 1
            else:
                del self.replace_depth
                if not hasattr(self, 'replaces'):
                    self.replaces = []
                    pass
                self.replaces.append((self.replacing, self.replace_start, self.get_pos_end_tag()))
                pass
        elif hasattr(self, 'depth'):
            if self.depth > 0:
                self.depth -= 1
                pass
            else:
                del self.depth
                if self.doc_type == 'crate':
                    content = self.get_doc_range(self.start_pos, self.get_pos_end_tag())
                    print('%s\n</section>' % content)
                    pass
                elif self.doc_type == 'fn':
                    print('%s\n</section>' % self.get_doc_range(self.start_pos, self.get_pos_end_tag()))
                    self.doc_type = ''
                    pass
                pass
            pass
        pass
    pass
                

print('<html>')
print('<head>')
print('<link rel="preload" as="font" type="font/woff2" crossorigin href="../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../SourceCodePro-Semibold.ttf.woff2">')
print('<link rel="stylesheet" type="text/css" href="../normalize.css"><link rel="stylesheet" type="text/css" href="../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" type="text/css" href="../ayu.css" disabled><link rel="stylesheet" type="text/css" href="../dark.css" disabled><link rel="stylesheet" type="text/css" href="../light.css" id="themeStyle">')
print('<link rel="stylesheet" href="../noscript.css">')
print('''<style>
.tooltip.ignore {
 visibility: hidden;
}
.out-of-band {
 visibility: hidden;
}
.example-wrap {
 display: block;
 height: 30px;
 overflow: hidden;
 user-select: none;
}
.example-wrap::before {
 content: '......<<EXAMPLE>>......';
}
.item-decl {
 display: block;
 height: 30px;
 overflow: hidden;
 user-select: none;
}
.item-decl::before {
 content: '......<<CODE BLOCK>>......';
}
</style>
''')
print('</head>')
print('<body>')

for page in pages:
    print('<page filename="%s">' % page)
    p = MyParser()
    fo = open('blazesym/' + page, 'r')
    data = fo.read()
    p.raw_data = data
    p.feed(data)
    print('</page>')
    pass

print('</body>')
print('</html>')