#!/usr/bin/env python
# coding: utf-8

# # Lines
# 
# We show how the pipeline detects lines on the page and we provide
# critical examples to see how successful the method is.
# 
# Reference: [lines](https://among.github.io/fusus/fusus/lines.html).

# In[1]:


get_ipython().run_line_magic('load_ext', 'autoreload')
get_ipython().run_line_magic('autoreload', '2')


# In[2]:


from fusus.book import Book


# In[3]:


B = Book(cd="~/github/among/fusus/example")


# In[4]:


# cd to the book directory
get_ipython().system('cd `pwd`')


# We show the line division in every block of text in every page.
# Check visually whether all lines have been detected correctly.
# 
# The `histogram` stage shows the blocks that have been detected on the page,
# and within the blocks the histograms that correspond to the ink distribution.
# 
# We mark the start and end of lines by orange and purple dots, which are
# obtained by a rolling median filter over the first and last black pixel position on each pixel line.
# 
# In each block the main line bands are shown.
# A green rule marks the start of a band, a red rule the end.
# The space between bands is greyed out.
# We show the `main` bands, which are derived directly from the histogram.
# 
# The main bands may not contain *all* the ink, but do not worry: the bands are used to target
# the cleaning of marks, and are not visible to the rest of the processing stages.
# 
# Check in particular:
# * whether short lines have been detected
# * whether consecutive lines are not treated as one line.
# 
# Page 101 is a critical page: both errors are likely to occur!

# In[5]:


def checkLines(pg, quiet=True, **kwargs):
    if pg is None:
        for pg in B.allPagesList:
            page = B.process(
                batch=False,
                pages=pg,
                doOcr=False,
                uptoLayout=True,
                quiet=quiet,
                **kwargs,
            )
            page.show(stage="histogram")
    else:
        page = B.process(
            batch=False,
            pages=pg,
            doOcr=False,
            uptoLayout=True,
            quiet=quiet,
            **kwargs,
        )
        page.show(stage="histogram")
    return page


# In[6]:


# B.configure(blurY=None, peakSignificant=0.1, peakProminenceY=None, valleyProminenceY=None, debug=0)


# ## Check a single page

# In[7]:


page = checkLines(101)


# ## Check all pages

# In[8]:


page = checkLines(None)


# In[ ]: