Re: [GIT PULL] License cleanup: add SPDX license identifiers to some kernel files

[Greg KH]

On Thu, Nov 02, 2017 at 10:32:17AM -0700, Linus Torvalds wrote:
> On Thu, Nov 2, 2017 at 10:25 AM, Linus Torvalds
> <torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:
> >
> > So to me, the "just put it as the first syntactically possible line,
> > and just always use the same comment format" is simply to avoid
> > unnecessary arguments/conflicts about which of any number of ways you
> > *could* do it.
> 
> Side note: I'm not going to enforce it, it's just a personal wish to
> hopefully make my life easier.
> 
> This pull request from Greg already has different comment formats for
> different files. I pulled it despite that.

It should have been consistent, everything except the script files went
as the first line of the file.

For .h files, we had to use /* */
For .c files, we used //
For scripts, and asm, we used the comment "marker" that was used in the
file already.

Attached is the script written by Thomas and tweaked by me to do all of
the tag insertion based on a csv file, it picks the format based on the
name and content of the file.

thanks,

greg k-h
#!/usr/bin/env python
#
import sys
import os

def insert_at(srclines, pos, tag, style):
    if style == '/*':
        srclines.insert(pos, '/* SPDX-License-Identifier: %s */\n' %tag)
    else:
        srclines.insert(pos, '%s SPDX-License-Identifier: %s\n' %(style, tag))
    return True

def handle_c(srclines, tag):
    return insert_at(srclines, 0, tag, '//')

def is_script(srclines):
    for line in srclines:
        line.lstrip();
        if line.startswith('#!'):
            return True;
    return False;

def handle_asm(srclines, tag):
    # Stupid search for a proper style to comment the SPDX tag
    pos = 0
    style = None
    for line in srclines:
        pos += 1
        line.lstrip();
        if line.startswith(';;;'):
            style = ';;;'
        elif line.startswith(';;'):
            style = ';;'
        elif line.startswith(';'):
            style = ';'
        elif line.startswith('|'):
            style = '|'
        elif line.startswith('!'):
            style = '!'
        elif line.startswith('//'):
            style = '//'
        elif line.find("/*") >= 0:
            style = '/*'
        else:
            # default to /* if we have no clue
            style = '/*'
        return insert_at(srclines, 0, tag, style)
    return False

def handle_sh(srclines, tag):
    return insert_at(srclines, 1, tag, '#')

tf = open(sys.argv[1])

for entry in tf.readlines():

    if len(entry.strip()) == 0:
        continue

    nr, fname, tag = entry.strip().split(',')
    # FIXME: Use a proper encoder
    fname = fname.replace('%2C',',')
    fname = fname.replace('%2B','+')
    if tag == 'NOTAG':
        print("Skipping %s" %fname)
        continue

    if not os.path.isfile(fname):
        print("FAIL: File %s does not exist anymore" %fname)
        continue

    bname = os.path.basename(fname)
    
    srclines = open(fname).readlines()

    done = False
    for line in srclines:
        if line.find('SPDX-License-Identifier') >= 0:
            done = True
            break

    if done:
        print("SPDX id exists already in %s" %fname)
        continue

    ok = False
    if fname.endswith('.h') or fname.endswith('.lds'):
        ok = insert_at(srclines, 0, tag, '/*')

    elif fname.endswith('.cpp'):
        ok = insert_at(srclines, 0, tag, '//')

    elif fname.endswith('.c') or fname.endswith('.uc'):
        ok = handle_c(srclines, tag)

    elif fname.endswith('.S'):
        ok = handle_asm(srclines, tag)

    elif fname.endswith('.cocci'):
        ok = insert_at(srclines, 0, tag, '//')
        
    elif fname.endswith('.dts') or fname.endswith('.dtsi'):
        ok = insert_at(srclines, 0, tag, '//')

    elif fname.endswith('.py') or fname.endswith('.tc') or fname.endswith('.sh') or fname.endswith('.pl'):
        ok = insert_at(srclines, 1, tag, '#')

    elif bname.startswith('Makefile') or bname.startswith('Kconfig') or bname.startswith('Kbuild'):
        ok = insert_at(srclines, 0, tag, '#')

    elif is_script(srclines):
        ok = insert_at(srclines, 1, tag, "#")

    else:
        print("Unhandled or ignored file %s" %fname)
        continue

    if ok:
        open(fname, 'w').writelines(srclines)
        print("Inserted %s into %s" %(tag, fname))
    else:
        print("FAIL: No place for insertion found %s" %fname)